© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9813
    Prev
    Next
    INDEX
    Explanations

    cannot and will not fulfill

    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_13_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
     muffin
    0.35
    А
    0.33
     M
    0.32
    rl
    0.31
     А
    0.31
    rm
    0.31
    YOUR
    0.31
    rett
    0.30
    INES
    0.30
     MEDICAL
    0.30
    POSITIVE LOGITS
     Domen
    0.35
    dolo
    0.35
    ścio
    0.33
     Ship
    0.32
     Hud
    0.32
    ᴢ
    0.32
    tamil
    0.32
     Nap
    0.31
     เหรอ
    0.31
    传说
    0.31
    Activations Density 0.044%

    No Known Activations