© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 46848
    Prev
    Next
    INDEX
    Explanations

    public:

    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_10_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
    0.34
    ;
    0.30
    IN
    0.30
     biy
    0.25
    !
    0.25
    fat
    0.24
    ?
    0.24
    '
    0.24
    way
    0.24
    :
    0.24
    POSITIVE LOGITS
    小
    0.27
     پانچ
    0.25
    用
    0.25
    妻子
    0.24
    的
    0.24
    を利用
    0.23
    位置
    0.23
    وني
    0.23
    是非常
    0.22
    ول
    0.22
    Activations Density 0.003%

    No Known Activations