© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 85841
    Prev
    Next
    INDEX
    Explanations

    installation **of**

    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_3_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
     сайты
    0.89
    K
    0.86
    OR
    0.86
    O
    0.86
    Bsky
    0.84
    ER
    0.83
    transistors
    0.83
    strass
    0.83
    ,_-
    0.82
    бору
    0.82
    POSITIVE LOGITS
    of
    0.93
    ۔
    0.80
     in
    0.77
     در
    0.77
    ни
    0.76
    6
    0.74
    ne
    0.74
    5
    0.72
     by
    0.72
    ht
    0.71
    Activations Density 0.002%

    No Known Activations