© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205487
    Prev
    Next
    INDEX
    Explanations

    United Nations or UN associated information

    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_37_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
     Masks
    0.41
     IRE
    0.40
    food
    0.38
     STAFF
    0.37
    𝔸
    0.37
    ẹp
    0.37
    pperware
    0.37
    pops
    0.36
    灭
    0.36
     LSM
    0.36
    POSITIVE LOGITS
    сног
    0.41
     SwitchCompat
    0.38
    માન્ય
    0.38
    蛩
    0.36
     trails
    0.36
     केंद्रित
    0.36
     documentos
    0.35
    covariant
    0.35
     documents
    0.35
    দুল
    0.34
    Activations Density 0.000%

    No Known Activations