© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 261449
    Prev
    Next
    INDEX
    Explanations

    large language model

    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
     psychos
    0.42
     Projek
    0.42
    𝗍
    0.40
    antikan
    0.40
    ίας
    0.40
     või
    0.40
     та
    0.39
     eller
    0.39
    soldiers
    0.39
     Soldaten
    0.39
    POSITIVE LOGITS
     hunt
    0.42
    rgb
    0.42
     机
    0.40
    崤
    0.40
     erud
    0.40
    Ir
    0.39
     nắm
    0.39
    ണി
    0.38
    website
    0.38
    レポート
    0.38
    Activations Density 0.007%

    No Known Activations