© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 221158
    Prev
    Next
    INDEX
    Explanations

    conversations, updates, month, glamorous, pharmacological

    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_10_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
    干燥
    0.52
    ㅃ
    0.47
    ologous
    0.45
     జరిగ
    0.44
    ವಾಗಿ
    0.43
     அழைத்து
    0.43
     తగ్గి
    0.43
    くなる
    0.42
     Prothorax
    0.42
     ocorre
    0.42
    POSITIVE LOGITS
     =
    0.49
    neighborhood
    0.48
    Stream
    0.47
    config
    0.46
    dist
    0.46
     filming
    0.45
    ademia
    0.44
    custom
    0.44
    parameter
    0.43
    research
    0.42
    Activations Density 0.000%

    No Known Activations