© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42535
    Prev
    Next
    INDEX
    Explanations

    purposes

    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
     rapid
    0.43
     extraordinarily
    0.40
    Notify
    0.37
     extremely
    0.36
     best
    0.36
     pound
    0.36
    .*
    0.36
     sensational
    0.35
    Bell
    0.34
    surprise
    0.34
    POSITIVE LOGITS
    拍攝
    0.48
    埸
    0.46
     Bucket
    0.46
     बुन्देल
    0.45
     маник
    0.45
    醮
    0.44
    ográfico
    0.42
     richten
    0.42
     coleção
    0.42
     Produtos
    0.41
    Activations Density 0.000%

    No Known Activations