© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6071
    Prev
    Next
    INDEX
    Explanations

    words, numbers, and symbols used for sporting event reporting.

    oai_token-act-pair · gemini-2.0-flash

    brackets/separators

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    cửa
    -0.49
    验证码
    -0.46
    ensä
    -0.46
    wände
    -0.45
     Wikimedijinoj
    -0.45
    lorette
    -0.45
     AssertionError
    -0.45
    isNew
    -0.45
    $\%
    -0.45
    CORO
    -0.44
    POSITIVE LOGITS
     resourceCulture
    0.68
     transfieras
    0.62
    WireFormat
    0.62
     AssemblyCulture
    0.60
    Personendaten
    0.59
    mergeFrom
    0.56
     frattempo
    0.55
    WarningLevel
    0.52
     cervello
    0.51
     Paramètres
    0.50
    Activations Density 12.521%

    No Known Activations