© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 198178
    Prev
    Next
    INDEX
    Explanations

    hissing sound

    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_9_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
    ০০
    0.71
    情况下
    0.63
    时候
    0.63
    鐪
    0.62
     hason
    0.61
    ارك
    0.60
    代言
    0.60
    䀖
    0.60
    抱
    0.59
    疇
    0.59
    POSITIVE LOGITS
    us
    1.22
    y
    1.19
    ade
    1.05
    ad
    1.03
    s
    0.98
    k
    0.93
    z
    0.92
    b
    0.90
    ung
    0.86
    u
    0.85
    Activations Density 0.010%

    No Known Activations