© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 49967
    Prev
    Next
    INDEX
    Explanations

    assumes a

    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_31_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
    hemer
    0.33
    Sac
    0.33
    চিত্রে
    0.33
    ሼ
    0.33
     landmarks
    0.32
     ማን
    0.31
     believing
    0.31
     मेगापिक्सल
    0.31
    랜드
    0.30
     disregarding
    0.30
    POSITIVE LOGITS
     вос
    0.33
     Contribute
    0.33
    狈
    0.32
     improved
    0.32
    improved
    0.32
    라는
    0.32
    changed
    0.31
    increased
    0.31
     increased
    0.31
    某种
    0.31
    Activations Density 0.016%

    No Known Activations