© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14172
    Prev
    Next
    INDEX
    Explanations

    code snippets related to scripting

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     
    -0.55
    -
    -0.51
    :
    -0.48
    .
    -0.47
     or
    -0.46
     a
    -0.43
    ?
    -0.43
     and
    -0.43
     –
    -0.40
     вы
    -0.40
    POSITIVE LOGITS
     myſelf
    1.20
     itſelf
    1.05
     becauſe
    1.04
     Monfieur
    1.02
    setVerticalGroup
    1.02
    IntoConstraints
    0.98
    Personensuche
    0.97
     Theſe
    0.96
    fjspx
    0.96
    存于互联网档案馆
    0.96
    Activations Density 4.994%

    No Known Activations