© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130763
    Prev
    Next
    INDEX
    Explanations

    general rule

    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_6_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
    on
    1.42
    r
    1.35
    es
    1.28
    im
    1.23
    x
    1.16
    as
    1.14
    ad
    1.13
    et
    1.12
    en
    1.11
    id
    1.11
    POSITIVE LOGITS
    </h2>
    1.14
     tequila
    1.12
     an
    1.02
     fireplace
    1.02
     starfish
    1.02
    ;
    1.02
    ﻤ
    1.01
     hairdryer
    1.00
    </b>
    1.00
    لی
    0.99
    Activations Density 0.000%

    No Known Activations