© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17267
    Prev
    Next
    INDEX
    Explanations

    Hey everyone, and welcome

    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_34_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
     enterprises
    0.40
    企业
    0.38
     Firma
    0.38
    问
    0.36
    ذی
    0.35
    šky
    0.35
     enterprise
    0.34
     Collider
    0.34
    স্পতিবার
    0.33
     poroz
    0.33
    POSITIVE LOGITS
    нке
    0.39
    ;++
    0.38
    ᆼ
    0.38
    },"
    0.37
     wieder
    0.37
    ู่
    0.37
     nuevamente
    0.36
    راف
    0.36
     monuments
    0.36
    戍
    0.36
    Activations Density 0.006%

    No Known Activations