© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193986
    Prev
    Next
    INDEX
    Explanations

    gale force winds

    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_4_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
    ación
    0.96
    ра
    0.93
    ی
    0.92
    ンの
    0.91
    線の
    0.84
     linee
    0.84
    ет
    0.84
    ก็จะ
    0.84
     funzione
    0.83
    ためには
    0.82
    POSITIVE LOGITS
    1
    1.63
    G
    1.28
    Be
    1.14
    Data
    1.11
    5
    1.10
    4
    1.10
    7
    1.08
    #
    1.08
    N
    1.07
    B
    1.05
    Activations Density 0.001%

    No Known Activations