© 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. 14864
    Prev
    Next
    INDEX
    Explanations

    ew

    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_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
     l
    0.61
    ta
    0.56
    ail
    0.54
     overtaking
    0.51
     city
    0.50
     countries
    0.50
     roots
    0.50
    ipping
    0.49
    OTO
    0.49
     minimalist
    0.49
    POSITIVE LOGITS
    ἐ
    0.61
     “,
    0.55
    де
    0.55
     об
    0.55
     `,
    0.53
     发表于
    0.52
    ;,
    0.52
    鍰
    0.52
    провод
    0.52
     忄
    0.52
    Activations Density 0.007%

    No Known Activations