© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8875
    Prev
    Next
    INDEX
    Explanations

    code declaring public static variables

    oai_token-act-pair · gemini-2.0-flash

    static

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    BeginContext
    -0.51
    }`).
    -0.47
    )]
    -0.47
    ivably
    -0.47
     sumpay
    -0.45
    Parcelize
    -0.45
    ubah
    -0.44
    Література
    -0.43
     credere
    -0.42
    RefNanny
    -0.42
    POSITIVE LOGITS
     المعيارى
    0.82
    tvguidetime
    0.69
    ValueStyle
    0.65
     AssemblyCulture
    0.64
    دانشنامهٔ
    0.59
    soort
    0.57
    Panamoan
    0.56
    (:)
    0.56
     useStyles
    0.54
     Smiley
    0.53
    Activations Density 2.227%

    No Known Activations