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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12002
    Prev
    Next
    INDEX
    Explanations

    code snippets and mathematical expressions, especially the letter 'c' followed by other characters or symbols

    oai_token-act-pair · gemini-2.0-flash

    The letter c

    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
    c
    -1.13
    cat
    -0.95
    can
    -0.88
    cal
    -0.88
    cum
    -0.86
    car
    -0.85
    cas
    -0.84
    cs
    -0.80
    cin
    -0.79
    cra
    -0.77
    POSITIVE LOGITS
     C
    0.84
     CTC
    0.80
     CQ
    0.79
     ContentValues
    0.78
     CWE
    0.74
     CI
    0.73
     CP
    0.72
     cjs
    0.70
     c
    0.67
     CJ
    0.67
    Activations Density 3.201%

    No Known Activations