© 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. 12266
    Prev
    Next
    INDEX
    Explanations

    email addresses

    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
    ஈ
    0.43
    HRS
    0.39
    𒊩
    0.39
     Topology
    0.39
    と思いました
    0.38
    ভাঁ
    0.37
    ᱘
    0.37
    不足
    0.36
    headless
    0.36
     недостаточно
    0.36
    POSITIVE LOGITS
     neighbourhood
    0.41
     buyers
    0.40
     protection
    0.40
     cover
    0.39
     revel
    0.39
     neighborhood
    0.39
     source
    0.38
     plantation
    0.38
     bursting
    0.38
     spoilers
    0.38
    Activations Density 0.002%

    No Known Activations