© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42760
    Prev
    Next
    INDEX
    Explanations

    greetings and inquiries

    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_22_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
     armor
    0.33
    heavy
    0.32
    armor
    0.31
     heavyweight
    0.30
     grafts
    0.30
    pretty
    0.30
     hydrocarbon
    0.30
    ::-
    0.29
     stockp
    0.29
     conformance
    0.29
    POSITIVE LOGITS
     одино
    0.36
     Divided
    0.34
     Subdivision
    0.33
     Molecular
    0.33
     Lim
    0.32
     Lampung
    0.32
     divisible
    0.32
     Child
    0.32
     História
    0.32
     Sensors
    0.31
    Activations Density 0.017%

    No Known Activations