© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 195214
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_15_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
    ру
    0.59
    <0x0D>
    0.53
     n
    0.52
    0
    0.51
    -
    0.51
    </h2>
    0.50
     Neben
    0.50
     ночью
    0.50
    助
    0.47
    9
    0.47
    POSITIVE LOGITS
    詑
    0.54
    牴
    0.53
    ಗೊಂಡ
    0.50
    㵴
    0.48
    煖
    0.48
     정의역
    0.47
    烺
    0.46
    匤
    0.46
    潅
    0.46
    ITURE
    0.46
    Activations Density 0.000%

    No Known Activations