© 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. 178324
    Prev
    Next
    INDEX
    Explanations

    digit 8

    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
    erder
    0.40
    ᅪ
    0.37
     രജി
    0.36
    વાલ
    0.36
     Member
    0.36
     sebenarnya
    0.35
     Wirk
    0.35
     आठवीं
    0.35
     divisor
    0.34
     Qualifier
    0.34
    POSITIVE LOGITS
     түз
    0.38
    🈶
    0.38
     مكتب
    0.38
    迷
    0.37
    撳
    0.36
     पेशकश
    0.35
    SEVERE
    0.35
     полю
    0.35
    𠃊
    0.35
    ${\
    0.35
    Activations Density 0.005%

    No Known Activations