© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 46242
    Prev
    Next
    INDEX
    Explanations

    advice, help, prompt

    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_22_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
    诃
    0.42
     好
    0.35
    prova
    0.35
     města
    0.35
     για
    0.34
    淏
    0.34
     לפ
    0.33
    ~(
    0.33
     enqu
    0.33
     hasattr
    0.33
    POSITIVE LOGITS
     comedor
    0.38
    breakfast
    0.36
    𝗲
    0.36
     पूरी
    0.36
    cleaned
    0.34
     perfectly
    0.34
     invisible
    0.34
     аку
    0.34
    ended
    0.33
     बच्चन
    0.33
    Activations Density 0.012%

    No Known Activations