© 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. 227894
    Prev
    Next
    INDEX
    Explanations

    quotable lines

    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
    c
    1.32
    u
    1.22
    ল
    1.22
    in
    1.15
    ल
    1.09
    ot
    1.06
    리
    1.05
    𝟘
    1.05
    ar
    1.05
    on
    1.03
    POSITIVE LOGITS
    '
    1.26
     for
    1.05
     don
    0.92
    、
    0.90
    、“
    0.89
     is
    0.83
     bör
    0.82
     ვი
    0.82
    PL
    0.77
     einsch
    0.77
    Activations Density 0.000%

    No Known Activations