© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7726
    Prev
    Next
    INDEX
    Explanations

    code or discussion mentioning scrolling

    oai_token-act-pair · gemini-2.0-flash

    scroll

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     
    -1.37
     the
    -1.25
     in
    -1.25
     and
    -1.23
     a
    -1.20
     I
    -1.10
     is
    -1.08
     “
    -1.05
     A
    -1.02
     all
    -1.01
    POSITIVE LOGITS
     Theſe
    1.86
     myſelf
    1.80
     itſelf
    1.77
     Anſ
    1.75
     auffi
    1.74
     Houſe
    1.73
     Efq
    1.72
     ―――――
    1.70
     Monfieur
    1.68
     AssemblyCulture
    1.66
    Activations Density 1.417%

    No Known Activations