© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242933
    Prev
    Next
    INDEX
    Explanations

    data type checks

    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_40_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
     lap
    0.42
    Sue
    0.41
     nest
    0.40
     kasus
    0.40
    jv
    0.40
     landmarks
    0.40
    ඪ
    0.40
     disorders
    0.39
     soi
    0.39
     sue
    0.39
    POSITIVE LOGITS
    ALLOWED
    0.39
    ALLOW
    0.38
    Additive
    0.38
    BIND
    0.37
    ҡ
    0.37
    additive
    0.37
    ख
    0.36
    ยอม
    0.35
     ADD
    0.35
    ADD
    0.35
    Activations Density 0.000%

    No Known Activations