© 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. 133886
    Prev
    Next
    INDEX
    Explanations

    muttering about

    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
    h
    1.38
    ur
    1.27
    da
    1.25
    a
    1.20
    an
    1.19
    ar
    1.19
    ü
    1.18
    í
    1.13
    ab
    1.09
    to
    1.09
    POSITIVE LOGITS
     as
    1.02
    ｴ
    1.00
    स्पिटल
    0.96
    你
    0.93
    𝒆
    0.93
    н
    0.92
    zäh
    0.92
    𝘋
    0.90
     équip
    0.89
     bạn
    0.89
    Activations Density 0.001%

    No Known Activations