Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 6917
    Prev
    Next
    INDEX
    Explanations

    various keywords used in Java code like "if", "else", "for", "try", "catch", "static", "Nullable", etc.

    oai_token-act-pair · gemini-2.0-flash

    if

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    writeFieldEnd
    -1.07
    yntaxException
    -1.03
    Попис
    -0.82
     TextInputType
    -0.75
    IndentedString
    -0.74
    lapsingToolbar
    -0.73
    ValueStyle
    -0.71
    ViewFeatures
    -0.71
    HostException
    -0.70
     nakalista
    -0.70
    POSITIVE LOGITS
     «
    0.43
     comptes
    0.42
    «
    0.42
    Present
    0.39
    present
    0.39
     Kinney
    0.39
    DidChange
    0.39
     Económica
    0.39
    accepte
    0.39
    IMATE
    0.38
    Activations Density 0.225%

    No Known Activations