© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6434
    Prev
    Next
    INDEX
    Explanations

    format strings and related words as used in programming

    oai_token-act-pair · gemini-2.0-flash

    s

    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
    <bos>
    -0.81
    %")
    -0.61
     themſelves
    -0.57
    .”)
    -0.54
     whoſe
    -0.54
     []),
    -0.54
     itſelf
    -0.54
    !')
    -0.54
     the
    -0.54
    ]")
    -0.53
    POSITIVE LOGITS
     "..\..\
    0.99
    TypedDataSet
    0.93
     "..\..\..\
    0.84
    principalTable
    0.78
     cref
    0.78
    yntaxException
    0.77
    protoimpl
    0.77
    RepeatedField
    0.77
     wireType
    0.74
     resourceCulture
    0.73
    Activations Density 0.526%

    No Known Activations