© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34495
    Prev
    Next
    INDEX
    Explanations

    sweet dreams

    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_3_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
    i
    0.56
     sepsis
    0.54
    I
    0.54
     nessa
    0.51
    ו
    0.51
    一篇
    0.51
    다라고
    0.51
    uously
    0.49
    션을
    0.49
     surgiu
    0.49
    POSITIVE LOGITS
    。
    0.73
     of
    0.69
    。</
    0.68
    ）、
    0.65
     esterno
    0.65
    。\
    0.65
    》、《
    0.64
    ）
    0.64
    RO
    0.63
     étrangers
    0.63
    Activations Density 0.000%

    No Known Activations