© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158004
    Prev
    Next
    INDEX
    Explanations

    duct tape and related items

    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_2_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
     have
    1.08
    a
    1.02
     at
    0.98
    ва
    0.96
    ो
    0.96
     be
    0.94
     था
    0.93
    institut
    0.92
    enie
    0.91
     aude
    0.91
    POSITIVE LOGITS
     in
    1.75
    ও
    1.55
    도
    1.50
    在
    1.48
    ח
    1.43
    も
    1.30
    ی
    1.20
    та
    1.11
    ین
    1.10
    א
    1.09
    Activations Density 0.001%

    No Known Activations