© 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. 11411
    Prev
    Next
    INDEX
    Explanations

    contact information and addresses

    oai_token-act-pair · gemini-2.0-flash

    contact information keywords

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

    Extract identifiers and data

    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
     baik
    -0.38
     fiches
    -0.38
    ず
    -0.38
     per
    -0.35
    People
    -0.35
    bo
    -0.35
    行的
    -0.35
    рт
    -0.34
     isto
    -0.34
    стам
    -0.34
    POSITIVE LOGITS
    thâu
    0.95
    ValueStyle
    0.93
    Tikang
    0.87
    
    0.85
     Италијани
    0.85
    expandindo
    0.85
     ExecuteAsync
    0.85
     snippetHide
    0.84
    Ecotoxicity
    0.81
    exitRule
    0.81
    Activations Density 2.494%

    No Known Activations