© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144642
    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_0_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
     평가
    0.60
     hầu
    0.56
     уго
    0.55
     ইউনিক
    0.55
    🍃
    0.54
     সৌরভ
    0.53
     тести
    0.53
     выпла
    0.53
     忄
    0.53
    萸
    0.51
    POSITIVE LOGITS
    on
    0.63
    ou
    0.55
    il
    0.53
    ir
    0.52
    ai
    0.51
    は
    0.51
    r
    0.50
    is
    0.50
    val
    0.50
    or
    0.50
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.