© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 31331
    Prev
    Next
    INDEX
    Explanations

    software libraries and interfaces

    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_7_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
    ا
    0.32
     tại
    0.32
    ﻚ
    0.31
     директора
    0.31
    ウン
    0.29
    다
    0.29
    的服务
    0.29
    𝒖
    0.29
    在庫
    0.29
    i
    0.29
    POSITIVE LOGITS
    ing
    0.44
    s
    0.42
    sh
    0.38
    ler
    0.37
    us
    0.36
    ased
    0.36
    sl
    0.36
    ly
    0.35
    pan
    0.34
    (
    0.34
    Activations Density 0.145%

    No Known Activations