© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 202705
    Prev
    Next
    INDEX
    Explanations

    Verse

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    "=
    0.40
    ?=
    0.39
    .-(
    0.39
    ,=
    0.38
    IOD
    0.37
    -=
    0.36
    νει
    0.36
     Ρ
    0.35
    getModel
    0.35
    kil
    0.34
    POSITIVE LOGITS
    ੴ
    0.38
    を実行
    0.38
    ተኛ
    0.38
    दात
    0.38
    ectic
    0.37
     Goll
    0.37
     dold
    0.37
    пь
    0.36
    clr
    0.36
    jols
    0.36
    Activations Density 0.000%

    No Known Activations