© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5712
    Prev
    Next
    INDEX
    Explanations

    words related to legal proceedings or testimony

    oai_token-act-pair · gemini-2.0-flash

    non-English terms and identifiers

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

    questions and answers

    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
     response
    -3.06
     Response
    -2.77
    response
    -2.63
     responses
    -2.63
     RESPONSE
    -2.47
    Response
    -2.45
     respond
    -2.44
     responded
    -2.38
     Responses
    -2.36
     responding
    -2.34
    POSITIVE LOGITS
     يتيمه
    0.73
     AssemblyTitle
    0.62
    EDEFAULT
    0.61
     мәкал
    0.61
    يكب
    0.60
    CPtr
    0.59
    الإنجليزية
    0.59
    LLocation
    0.58
     Référence
    0.58
    HasAnnotation
    0.58
    Activations Density 2.719%

    No Known Activations