© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216192
    Prev
    Next
    INDEX
    Explanations

    height measurements

    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_31_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
     inches
    0.44
     timescales
    0.41
     timescale
    0.41
    ﮯ
    0.40
     stocking
    0.40
     WebSocket
    0.39
     Inches
    0.39
     ఇప్పుడు
    0.38
     WEBSITE
    0.38
     expenditure
    0.37
    POSITIVE LOGITS
    .).
    0.39
    Mayo
    0.38
    rab
    0.38
    بان
    0.38
    ()}")
    0.37
     Alford
    0.37
    راهيم
    0.37
     공간
    0.36
    тері
    0.36
    Passive
    0.36
    Activations Density 0.002%

    No Known Activations