© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142624
    Prev
    Next
    INDEX
    Explanations

    central China

    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_0_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
    j
    1.70
     as
    1.46
    x
    1.45
    ض
    1.45
    و
    1.42
    g
    1.32
    ↵
    1.31
    z
    1.31
    ى
    1.30
    يد
    1.27
    POSITIVE LOGITS
    ς
    1.18
    1.00
     It
    0.97
    ।
    0.93
    🍡
    0.89
    🍤
    0.86
    (<
    0.84
    ALO
    0.82
     لگتا
    0.81
    нку
    0.80
    Activations Density 0.036%

    No Known Activations