© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108728
    Prev
    Next
    INDEX
    Explanations

    особенно в

    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
    ם
    1.55
    ר
    1.53
    ה
    1.51
    ן
    1.34
     I
    1.18
    ಿಂದ
    1.15
    מ
    1.11
     The
    1.04
     A
    1.00
     E
    0.99
    POSITIVE LOGITS
    д
    1.02
    s
    0.94
    ti
    0.92
    kort
    0.92
    dauer
    0.92
    goers
    0.91
    kaj
    0.91
    diği
    0.90
    daten
    0.89
    stellar
    0.89
    Activations Density 0.000%

    No Known Activations