© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134122
    Prev
    Next
    INDEX
    Explanations

    statements made

    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_6_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
    ۰
    1.21
    ០
    0.98
    ח
    0.96
    ifting
    0.94
    iging
    0.89
    羪
    0.88
    ０
    0.88
    ٠
    0.88
    ᚕ
    0.85
    imbing
    0.84
    POSITIVE LOGITS
    '
    1.88
    s
    1.57
    ’
    1.33
    5
    1.18
    is
    1.07
    P
    1.05
    G
    1.02
    3
    1.00
    6
    0.99
    (
    0.97
    Activations Density 0.002%

    No Known Activations