© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 218377
    Prev
    Next
    INDEX
    Explanations

    Author: Your Name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     selections
    0.39
    难
    0.38
     renovating
    0.38
     renovated
    0.37
     selected
    0.36
     renov
    0.36
    Ancest
    0.36
     Rankings
    0.36
     Axis
    0.35
    $};
    0.35
    POSITIVE LOGITS
    BID
    0.38
    とう
    0.37
     fly
    0.36
    جون
    0.36
    FreeBuf
    0.36
    like
    0.35
    盾
    0.35
    ウザ
    0.35
    laugh
    0.34
    嫁
    0.34
    Activations Density 0.000%

    No Known Activations