© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44198
    Prev
    Next
    INDEX
    Explanations

    learning to code

    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
    ኔታ
    0.59
    encerramento
    0.53
    தியான
    0.52
     chiamata
    0.51
    右
    0.50
     circost
    0.50
    Ⲓ
    0.50
    她的
    0.49
    immune
    0.49
    lossen
    0.49
    POSITIVE LOGITS
     ol
    0.54
     hips
    0.52
     follows
    0.51
    c
    0.50
    {}
    0.49
     shingles
    0.49
    स
    0.47
     employed
    0.46
     waves
    0.46
     weeds
    0.46
    Activations Density 0.013%

    No Known Activations