© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215661
    Prev
    Next
    INDEX
    Explanations

    isches Verhalten, .sch behavior, -sky power

    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_5_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
    dogs
    1.23
    ders
    1.22
    Від
    1.14
    靂
    1.13
    dgs
    1.13
    كان
    1.12
    daughters
    1.12
    kans
    1.11
    ਰ
    1.10
    филлер
    1.09
    POSITIVE LOGITS
     be
    1.66
     de
    1.41
    ")
    1.41
    in
    1.37
     di
    1.34
     on
    1.32
    s
    1.28
     he
    1.22
     e
    1.16
    聽
    1.15
    Activations Density 0.000%

    No Known Activations