© 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. 108628
    Prev
    Next
    INDEX
    Explanations

    álgebra, álbum, árabe

    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
    '
    1.74
    n
    1.65
    ak
    1.61
    AK
    1.56
    to
    1.42
    y
    1.42
    et
    1.41
    p
    1.41
    not
    1.36
    Z
    1.34
    POSITIVE LOGITS
    л
    2.31
    ل
    1.93
    し
    1.66
    ल
    1.65
    ল
    1.59
    ی
    1.56
    ם
    1.55
    ע
    1.55
    ל
    1.53
    ル
    1.50
    Activations Density 0.000%

    No Known Activations