© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10924
    Prev
    Next
    INDEX
    Explanations

    dates, times, URLs and some punctuation

    oai_token-act-pair · gemini-2.0-flash

    3

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Sixth
    -0.97
     sixth
    -0.95
     Fifth
    -0.94
     fifth
    -0.88
    Sixth
    -0.84
    Fifth
    -0.82
    sixth
    -0.78
     Six
    -0.77
    fifth
    -0.77
    fjspx
    -0.75
    POSITIVE LOGITS
    3
    0.92
     three
    0.78
    ৩
    0.74
    three
    0.73
     Three
    0.73
    ₃
    0.70
    三
    0.66
    Three
    0.66
    ３
    0.66
     THREE
    0.64
    Activations Density 3.302%

    No Known Activations