© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 96972
    Prev
    Next
    INDEX
    Explanations

    ash

    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_14_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
    am
    0.64
    ed
    0.61
    `)
    0.60
    e
    0.57
    es
    0.55
    an
    0.54
    ea
    0.54
    ])
    0.52
    »)
    0.50
     miatt
    0.50
    POSITIVE LOGITS
     요
    0.67
     디자인
    0.67
    LE
    0.61
     흰
    0.61
     Design
    0.59
     फ्रेम
    0.57
    オ
    0.57
     프
    0.56
     Cultura
    0.55
     Freestyle
    0.55
    Activations Density 0.000%

    No Known Activations