© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 235937
    Prev
    Next
    INDEX
    Explanations

    big

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    ilmesi
    0.38
    كام
    0.37
    ativi
    0.36
     قوم
    0.36
    ེ་
    0.36
     مط
    0.35
    }^{+},
    0.35
    왈
    0.35
    ಪಟ್ಟ
    0.35
    лях
    0.34
    POSITIVE LOGITS
     große
    0.60
     large
    0.60
     problem
    0.57
     كبيرة
    0.55
     большим
    0.55
     большой
    0.55
     grandes
    0.54
    large
    0.54
     grandi
    0.54
     grote
    0.54
    Activations Density 0.002%

    No Known Activations