© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45001
    Prev
    Next
    INDEX
    Explanations

    god, hear, help, love

    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_3_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
    と
    0.71
    ة
    0.60
    ン
    0.59
    0
    0.57
    와
    0.54
    ote
    0.52
     и
    0.52
    ↵↵
    0.51
     και
    0.51
    </th>
    0.49
    POSITIVE LOGITS
    ش
    0.80
    ח
    0.79
    نا
    0.75
    দ
    0.75
    ي
    0.67
    ح
    0.67
    سلم
    0.65
    ur
    0.65
    ज
    0.65
    서
    0.64
    Activations Density 0.003%

    No Known Activations