© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130690
    Prev
    Next
    INDEX
    Explanations

    janitorial, anisotropy, isotropy

    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_1_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
     a
    1.41
     an
    1.39
     as
    1.39
    هم
    1.38
     be
    1.33
     I
    1.30
    .
    1.16
     that
    1.14
    ם
    1.14
    ้
    1.13
    POSITIVE LOGITS
    n
    1.49
    f
    1.25
    and
    1.20
    ad
    1.16
    r
    1.13
    o
    1.09
    isub
    1.04
    on
    1.02
    oq
    1.02
    an
    1.01
    Activations Density 0.000%

    No Known Activations