© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79379
    Prev
    Next
    INDEX
    Explanations

    code delimiters and syntax

    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_0_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
     in
    1.27
    inib
    1.27
    in
    1.23
    ing
    1.22
    在
    1.19
    न
    1.16
    ਸ
    1.14
     hostels
    1.11
    बी
    1.09
    จะ
    1.09
    POSITIVE LOGITS
    。
    1.45
    ле
    1.42
    ே
    1.38
    ot
    1.38
    ா
    1.36
    다
    1.29
    ি
    1.23
    、《
    1.20
    larda
    1.16
    lardan
    1.16
    Activations Density 0.000%

    No Known Activations