© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215549
    Prev
    Next
    INDEX
    Explanations

    blame, blister, blouse, blinds

    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_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
    P
    1.42
     .
    1.41
    H
    1.38
    W
    1.34
    N
    1.30
     be
    1.30
    S
    1.27
    $
    1.27
    Y
    1.27
    V
    1.17
    POSITIVE LOGITS
    ant
    1.24
     consents
    1.22
    ين
    1.15
    tains
    1.15
    터를
    1.11
    ット
    1.10
    rames
    1.05
    tries
    1.05
    tong
    1.03
    ንዳንድ
    1.03
    Activations Density 0.002%

    No Known Activations