© 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. 42145
    Prev
    Next
    INDEX
    Explanations

    names ending in "-issa" or "-ena"

    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
    '
    1.23
    i
    1.09
    et
    1.08
    n
    1.00
    p
    0.98
    s
    0.97
    l
    0.96
    on
    0.92
    in
    0.89
    x
    0.87
    POSITIVE LOGITS
    ס
    1.07
    ية
    0.83
    וה
    0.82
    ội
    0.81
    ض
    0.80
    ו
    0.80
    سي
    0.75
     -\
    0.75
    )&=
    0.75
     chậm
    0.75
    Activations Density 0.006%

    No Known Activations