© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50369
    Prev
    Next
    INDEX
    Explanations

    think of it like

    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_30_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
     ওয়েবসাইট
    0.36
    अर्ज
    0.36
     dilution
    0.35
    мова
    0.33
    丷
    0.32
    紝
    0.32
     selle
    0.32
     FFA
    0.32
    াকিং
    0.32
     opet
    0.31
    POSITIVE LOGITS
    steiner
    0.33
    它是
    0.32
    It
    0.31
    Sebagai
    0.31
    sic
    0.31
     interpretive
    0.30
    wristwatch
    0.30
    !;
    0.30
    );
    0.30
    它
    0.30
    Activations Density 0.014%

    No Known Activations