© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231462
    Prev
    Next
    INDEX
    Explanations

    patriarch

    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_6_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
    us
    1.35
    ut
    1.34
    ot
    1.31
    t
    1.30
    i
    1.20
    for
    1.19
    '].
    1.13
    y
    1.12
    5
    1.02
    ko
    1.00
    POSITIVE LOGITS
    ين
    1.15
     on
    1.00
    ιν
    0.98
    ת
    0.92
     usuario
    0.91
     arquivo
    0.90
     comandos
    0.90
     képes
    0.90
    ב
    0.89
    נ
    0.89
    Activations Density 0.000%

    No Known Activations