© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 117453
    Prev
    Next
    INDEX
    Explanations

    .go code

    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_38_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
    her
    0.38
    ﯼ
    0.35
    ahal
    0.35
     бө
    0.34
     அறிவு
    0.34
     jū
    0.34
    }^{*},
    0.34
    唿
    0.34
     sở
    0.34
    ROW
    0.33
    POSITIVE LOGITS
     structs
    0.41
     Struct
    0.37
    ხვ
    0.37
    tego
    0.37
     Ding
    0.36
     হাসানের
    0.36
     APPE
    0.36
    sibling
    0.36
     افغانستان
    0.36
     Δεν
    0.35
    Activations Density 0.001%

    No Known Activations