© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3821
    Prev
    Next
    INDEX
    Explanations

    sentences that contain the word "thought" plus some related words and conjugations such as "intensional", "assume", "consider", and "sense"

    oai_token-act-pair · gemini-2.0-flash

    thought

    np_max-act · gemini-2.0-flash

    thought

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jsxFileName
    -0.46
    ContentAlignment
    -0.45
    TemporalType
    -0.44
    StoreMessageInfo
    -0.43
    uxxxx
    -0.42
     DbContext
    -0.42
    tableFuture
    -0.42
     encant
    -0.42
     Nebu
    -0.41
    に移
    -0.41
    POSITIVE LOGITS
    enderror
    0.61
    addContainerGap
    0.59
    Lähteet
    0.59
     بيها
    0.59
    исленность
    0.57
    jectures
    0.57
    iramente
    0.56
     hoped
    0.56
    abos
    0.56
     mergeFrom
    0.56
    Activations Density 1.427%

    No Known Activations