© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8046
    Prev
    Next
    INDEX
    Explanations

    alternative ways to phrase the concept of something happening despite something else using the word "spite" or "despite"

    oai_token-act-pair · gemini-2.0-flash

    contextually relevant conjunctions or phrases

    np_token-act-pair-logits · gpt-4o-mini

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    awtextra
    -0.96
     linkovi
    -0.94
    oneofs
    -0.92
    Vidite
    -0.90
    AndEndTag
    -0.87
    ThroughAttribute
    -0.87
    Autoritní
    -0.87
     tartalomajánló
    -0.86
    CloseOperation
    -0.85
    featureID
    -0.83
    POSITIVE LOGITS
     favor
    0.42
     menengah
    0.42
     \
    0.41
    těte
    0.39
    6
    0.39
     x
    0.39
     mid
    0.39
    as
    0.39
     as
    0.39
    Workbook
    0.38
    Activations Density 4.580%

    No Known Activations