© 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. 13194
    Prev
    Next
    INDEX
    Explanations

    code snippets and associated terms

    oai_token-act-pair · gemini-2.0-flash

    Code properties and nodes

    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
    <bos>
    -0.82
     Efq
    -0.73
     Majefty
    -0.68
     photolibrary
    -0.66
     itſelf
    -0.64
     Pues
    -0.64
     Cæsar
    -0.63
     myſelf
    -0.62
     Jefus
    -0.62
     himſelf
    -0.59
    POSITIVE LOGITS
    FormTagHelper
    0.69
    providedIn
    0.62
    SourceChecksum
    0.59
    randomUUID
    0.59
    EndProject
    0.57
    oredCriteria
    0.57
    sige
    0.57
    erover
    0.54
    MessageOf
    0.53
     BRO
    0.51
    Activations Density 15.155%

    No Known Activations