© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 260693
    Prev
    Next
    INDEX
    Explanations

    small, weights, weighting

    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_5_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
    يل
    1.45
    ש
    1.34
    。
    1.09
    "。
    1.04
    지
    1.02
    জ
    0.99
    ти
    0.98
     announcer
    0.97
    <h2>
    0.95
    ъ
    0.93
    POSITIVE LOGITS
    weight
    1.27
    вання
    1.19
    Ꮦ
    1.16
    convex
    1.16
    t
    1.16
    ᙱ
    1.13
    board
    1.10
    computing
    1.10
    water
    1.09
    می
    1.06
    Activations Density 0.000%

    No Known Activations