© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 102226
    Prev
    Next
    INDEX
    Explanations

    declarations and structure definitions

    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_16_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
     Datos
    0.49
     Trời
    0.49
     scores
    0.48
     datos
    0.47
    타
    0.47
    अन्य
    0.47
    ש
    0.47
     Mackey
    0.46
     wronged
    0.46
    럿
    0.46
    POSITIVE LOGITS
    ig
    0.59
    opoietic
    0.45
    ärke
    0.45
    ியே
    0.43
    il
    0.43
     proportions
    0.43
    igen
    0.42
    %,
    0.42
     अवलंब
    0.42
     Have
    0.42
    Activations Density 0.000%

    No Known Activations