© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103783
    Prev
    Next
    INDEX
    Explanations

    sencillos

    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_1_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
    z
    1.86
    ,
    1.44
    p
    1.37
    ;
    1.31
    q
    1.28
    '
    1.25
    i
    1.23
     \
    1.21
    ?
    1.16
    0
    1.12
    POSITIVE LOGITS
    ی
    1.55
    ری
    1.48
    ת
    1.41
    یت
    1.39
    ے
    1.34
    ین
    1.33
     contesto
    1.32
    ים
    1.31
    کی
    1.30
    یی
    1.25
    Activations Density 0.000%

    No Known Activations