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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6259
    Prev
    Next
    INDEX
    Explanations

    words and context related to charging someone with something in a legal sense

    oai_token-act-pair · gemini-2.0-flash

    legal terminology and charges

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

    charge

    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
     charge
    -2.92
     charges
    -2.61
     Charge
    -2.53
     charged
    -2.53
    charge
    -2.52
    Charge
    -2.38
     charging
    -2.31
     Charges
    -2.30
     CHARGE
    -2.28
    charges
    -2.16
    POSITIVE LOGITS
    SequentialGroup
    0.75
    EndProject
    0.52
     glyphicon
    0.50
    explique
    0.49
    ("")]
    0.48
    contr
    0.47
     مشين
    0.46
     comunale
    0.45
    </tfoot>
    0.45
    "])){
    0.45
    Activations Density 1.375%

    No Known Activations