© 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-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89097
    Prev
    Next
    INDEX
    Explanations

    code delimiters

    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_23_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
     Survival
    0.35
     alguien
    0.34
    mény
    0.32
    ///
    0.32
    entine
    0.32
     seemingly
    0.32
     Fee
    0.32
    简直
    0.32
     impec
    0.31
     pripre
    0.31
    POSITIVE LOGITS
     nix
    0.38
     流
    0.37
     ঃ
    0.36
     Вя
    0.34
    ویت
    0.33
     चिर
    0.33
     resolvers
    0.33
     basse
    0.32
     Withers
    0.32
    <0x18>
    0.31
    Activations Density 0.000%

    No Known Activations