© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 62067
    Prev
    Next
    INDEX
    Explanations

    plenty

    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_2_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
     I
    2.19
     with
    1.48
    ت
    1.46
    ת
    1.41
    т
    1.24
     as
    1.15
    with
    1.15
     M
    1.11
     K
    1.09
     N
    1.07
    POSITIVE LOGITS
    ad
    1.12
    ன்
    1.02
    ure
    1.00
     tại
    0.95
    anza
    0.93
    ang
    0.89
     primavera
    0.89
    ak
    0.89
     at
    0.89
    andex
    0.89
    Activations Density 0.000%

    No Known Activations