© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 177581
    Prev
    Next
    INDEX
    Explanations

    code separators

    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_29_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    izophren
    0.50
     REFERENCE
    0.47
     wys
    0.41
    uggish
    0.41
    izontal
    0.40
    ateful
    0.40
    𝓽
    0.40
    ╾
    0.40
     vedit
    0.40
     velmi
    0.39
    POSITIVE LOGITS
    Fe
    0.40
     No
    0.36
     Herman
    0.36
    No
    0.35
     основным
    0.35
     Jackson
    0.35
     Its
    0.34
    orde
    0.34
     খা
    0.33
     Mrs
    0.33
    Activations Density 0.000%

    No Known Activations