© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199435
    Prev
    Next
    INDEX
    Explanations

    geometry and measurements

    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_12_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
     HTMLSc
    0.40
     攵
    0.35
    ⓜ
    0.35
    🩹
    0.34
    弜
    0.34
    厷
    0.33
     sive
    0.33
     médec
    0.33
     Médico
    0.32
    比亚
    0.32
    POSITIVE LOGITS
     около
    0.29
    Когда
    0.28
    most
    0.28
    ainkan
    0.28
     L
    0.27
    has
    0.27
    もちろん
    0.27
     kaufen
    0.27
    -
    0.27
    لق
    0.26
    Activations Density 0.000%

    No Known Activations