© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142829
    Prev
    Next
    INDEX
    Explanations

    sx3

    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_0_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
    i
    1.86
    s
    1.84
    d
    1.64
    u
    1.64
    ra
    1.52
    t
    1.51
    ments
    1.32
    et
    1.30
    sons
    1.23
    dır
    1.22
    POSITIVE LOGITS
    是
    2.61
    は
    2.03
    는
    1.95
    ة
    1.89
    은
    1.82
     a
    1.72
     was
    1.53
    та
    1.52
    а
    1.51
    ви
    1.43
    Activations Density 0.000%

    No Known Activations