© 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. 134814
    Prev
    Next
    INDEX
    Explanations

    require statements

    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
     of
    0.98
    ко
    0.90
     ApJ
    0.88
    ா
    0.85
     on
    0.84
     Januar
    0.84
     ALJ
    0.83
     will
    0.82
     drank
    0.82
     EU
    0.80
    POSITIVE LOGITS
    S
    1.20
    I
    1.16
     و
    1.11
    F
    1.09
    M
    1.08
    O
    1.06
    C
    1.00
    และ
    0.99
    T
    0.99
    Ι
    0.98
    Activations Density 0.000%

    No Known Activations