© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7238
    Prev
    Next
    INDEX
    Explanations

    input axis horizontal vertical

    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_39_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
     रेल
    0.42
     comerci
    0.40
     vong
    0.37
     рабо
    0.37
    ន្ទ
    0.36
    團隊
    0.36
    ᐉ
    0.36
    дору
    0.36
     ভোগের
    0.36
    ៤
    0.36
    POSITIVE LOGITS
    取消
    0.38
    Cancel
    0.37
    ParseException
    0.36
     Helsinki
    0.36
    𝜁
    0.36
    攻撃
    0.36
    canceled
    0.36
     butter
    0.36
    Finland
    0.36
     authority
    0.35
    Activations Density 0.013%

    No Known Activations