© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12908
    Prev
    Next
    INDEX
    Explanations

    words associated with people dealing with problems, misdeeds, or difficult situations

    oai_token-act-pair · gemini-2.0-flash

    negative life events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     disambiguazione
    -0.79
    onAttach
    -0.65
    Espèce
    -0.60
     propOrder
    -0.56
    modelBuilder
    -0.56
    featureID
    -0.53
    SequentialGroup
    -0.52
    fromnode
    -0.51
    "]]
    -0.49
    TagHelper
    -0.48
    POSITIVE LOGITS
    setVerticalGroup
    0.64
    mobileqq
    0.62
    execSQL
    0.55
    endpush
    0.52
    andExpect
    0.51
    ymce
    0.51
    ToFile
    0.49
     Prophe
    0.49
    obat
    0.49
     dog
    0.48
    Activations Density 4.690%

    No Known Activations