© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14449
    Prev
    Next
    INDEX
    Explanations

    the word "was" and sometimes pronouns and possessive pronouns

    oai_token-act-pair · gemini-2.0-flash

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Jefus
    -0.77
     Houſe
    -0.77
     Majefty
    -0.72
     houſe
    -0.69
     ainfi
    -0.66
     fubject
    -0.66
     ſche
    -0.65
     dentaire
    -0.65
     meurt
    -0.65
    eramente
    -0.65
    POSITIVE LOGITS
    <bos>
    0.78
    nodoc
    0.67
     a
    0.62
    LookAnd
    0.62
    //
    0.60
    клопе
    0.59
    ⓧ
    0.59
    Datuak
    0.58
     Sk
    0.55
     Mal
    0.55
    Activations Density 0.410%

    No Known Activations