© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 182772
    Prev
    Next
    INDEX
    Explanations

    based on

    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
    Not in Any Lists

    No Comments

    Negative Logits
     diseases
    0.39
     Mainly
    0.37
    殃
    0.35
    >′
    0.35
     honesty
    0.34
    ఎ
    0.34
    size
    0.34
     aggravating
    0.34
    Plays
    0.33
    ;
    0.33
    POSITIVE LOGITS
    mittag
    0.46
     مخطط
    0.44
     සං
    0.41
    頷
    0.40
     Bhagavato
    0.40
    ների
    0.39
     sistemi
    0.38
    ທີ່ມີ
    0.38
    前辈
    0.37
    နှ
    0.37
    Activations Density 0.007%

    No Known Activations