© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9831
    Prev
    Next
    INDEX
    Explanations

    stealing from

    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_13_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
     hydrox
    0.61
    ("-
    0.58
     lineHeight
    0.57
     HOSP
    0.56
     되는
    0.55
    ﻭ
    0.54
    Periph
    0.54
    ize
    0.53
    cznym
    0.52
    izace
    0.52
    POSITIVE LOGITS
    .):
    0.60
    man
    0.55
    如下
    0.54
     extraneous
    0.53
     छात्र
    0.52
    カラ
    0.51
    ');
    0.51
    rador
    0.51
    .);
    0.50
     strenuous
    0.50
    Activations Density 0.000%

    No Known Activations