© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158102
    Prev
    Next
    INDEX
    Explanations

    AS (as in BLAS)

    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_2_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
    s
    2.44
    i
    2.02
    b
    1.65
    am
    1.64
    at
    1.60
    en
    1.52
    ي
    1.38
    y
    1.37
    is
    1.36
    in
    1.29
    POSITIVE LOGITS
     bruises
    1.09
    ರ್ಮ
    0.98
     расположение
    0.98
    ॉय
    0.97
     mortars
    0.96
     sermons
    0.95
     boroughs
    0.95
     scrapes
    0.95
     დროს
    0.94
     subalgebras
    0.93
    Activations Density 0.000%

    No Known Activations