© 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. 3870
    Prev
    Next
    INDEX
    Explanations

    a mix of conversion of one thing to another, digital to analog, decimal points, ratios, and bits

    oai_token-act-pair · gemini-2.0-flash

    Converting

    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
     conversion
    -2.55
     Conversion
    -2.38
     conversions
    -2.25
     convert
    -2.23
    Conversion
    -2.17
    conversion
    -2.16
     converted
    -2.13
     converting
    -2.08
     Convert
    -2.02
     converts
    -2.00
    POSITIVE LOGITS
    con
    0.81
    Con
    0.77
     Con
    0.71
     con
    0.69
    CON
    0.65
     kon
    0.63
     CON
    0.63
     Kon
    0.58
    Kon
    0.55
    TypedDataSet
    0.55
    Activations Density 1.722%

    No Known Activations