© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10942
    Prev
    Next
    INDEX
    Explanations

    color wheel, hue, saturation, sphere

    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_13_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
    U
    0.39
    into
    0.38
    P
    0.38
    J
    0.38
    oader
    0.37
    ل
    0.36
    ਲ
    0.36
    hr
    0.36
    lance
    0.36
    Н
    0.36
    POSITIVE LOGITS
     FER
    0.37
     Allora
    0.35
     warms
    0.34
    免許
    0.33
     wrongful
    0.33
     Alors
    0.32
     Mindanao
    0.32
     اليمن
    0.32
     తొలి
    0.32
     ME
    0.32
    Activations Density 0.035%

    No Known Activations