© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107880
    Prev
    Next
    INDEX
    Explanations

    cro/gro prefixes

    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
    ed
    1.52
     as
    1.43
    ти
    1.39
    y
    1.32
    al
    1.27
    ee
    1.27
    n
    1.27
    ется
    1.24
    ir
    1.23
    ።
    1.23
    POSITIVE LOGITS
    ’),
    1.14
    ل
    1.14
     indépend
    1.08
    the
    1.04
     прия
    1.03
    Y
    1.00
     végétaux
    1.00
    Hej
    0.99
     рус
    0.97
     relevante
    0.96
    Activations Density 0.000%

    No Known Activations