© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212275
    Prev
    Next
    INDEX
    Explanations

    skillet

    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_5_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
    s
    1.90
    ת
    1.43
    ים
    1.35
    V
    1.32
     on
    1.31
    T
    1.30
     is
    1.30
     was
    1.27
    F
    1.27
    بر
    1.21
    POSITIVE LOGITS
    ۰
    1.38
    ig
    1.09
    ri
    1.05
    ang
    1.04
    IN
    1.00
    ol
    0.99
    𝒆
    0.99
    <0x80>
    0.98
    ள்ளதாக
    0.96
    adays
    0.95
    Activations Density 0.000%

    No Known Activations