© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133790
    Prev
    Next
    INDEX
    Explanations

    pragmatic

    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_1_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
    .
    1.62
    re
    1.35
    。
    1.24
    ra
    1.09
    br
    1.06
    c
    1.05
    kan
    1.03
    ot
    1.02
    ala
    1.02
    pose
    1.01
    POSITIVE LOGITS
    스
    1.52
    어
    1.41
    나
    1.40
    u
    1.37
    ನ
    1.34
    та
    1.27
    क
    1.26
    в
    1.26
     the
    1.25
    성
    1.25
    Activations Density 0.001%

    No Known Activations