© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171999
    Prev
    Next
    INDEX
    Explanations

    deck of cards

    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_20_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
    bra
    0.48
    ব্র
    0.45
     несмотря
    0.44
    åd
    0.44
    iat
    0.44
    parser
    0.44
     ‘
    0.43
     apporte
    0.43
    opharm
    0.42
    பால்
    0.42
    POSITIVE LOGITS
    DISABLED
    0.46
    зів
    0.46
    籙
    0.45
     Calyce
    0.43
    лива
    0.43
     Epoxy
    0.42
    Issledovatel
    0.42
    ැල
    0.42
     epoxy
    0.41
    箓
    0.41
    Activations Density 0.000%

    No Known Activations