© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 205613
    Prev
    Next
    INDEX
    Explanations

    falsehoods

    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_10_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
    v
    0.69
    on
    0.67
    is
    0.66
    ap
    0.66
    ak
    0.64
     i
    0.63
    c
    0.62
    it
    0.60
    as
    0.59
    ī
    0.57
    POSITIVE LOGITS
    𒅴
    0.63
    🫤
    0.54
     energética
    0.53
     hinzufügen
    0.52
     Reinigung
    0.51
    uvial
    0.50
    ಬ್ಬಿಣ
    0.50
    clonal
    0.49
    ם
    0.49
    夠
    0.49
    Activations Density 0.000%

    No Known Activations