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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261246
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ar
    1.21
    ad
    1.13
    arza
    1.13
    (
    1.09
    arik
    1.02
    arap
    0.98
    al
    0.98
    arın
    0.96
    amate
    0.93
    kan
    0.92
    POSITIVE LOGITS
    с
    1.44
    of
    1.25
    س
    1.23
    number
    1.21
    ス
    1.20
    স
    1.12
    ﻀ
    1.06
    ма
    1.03
    ngày
    1.01
    記事
    0.96
    Activations Density 0.000%

    No Known Activations