© 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. 130688
    Prev
    Next
    INDEX
    Explanations

    fair value

    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
    見
    1.15
    お
    1.12
    し
    1.10
    出
    1.10
    ти
    1.08
    大
    1.07
    в
    1.05
    is
    1.03
    يل
    0.92
    使
    0.92
    POSITIVE LOGITS
     estimates
    1.05
    ant
    1.05
     Zidane
    1.05
     by
    1.02
     =
    1.00
     ay
    1.00
    el
    0.99
    ;
    0.98
    ों
    0.98
     adjustments
    0.97
    Activations Density 0.003%

    No Known Activations