© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 214206
    Prev
    Next
    INDEX
    Explanations

    premiums

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     Maked
    0.39
    Va
    0.38
    瓦
    0.37
     ва
    0.36
     وات
    0.34
    Depends
    0.34
     와
    0.34
     segregated
    0.34
    Nw
    0.34
     filede
    0.33
    POSITIVE LOGITS
    ôt
    0.46
    oto
    0.43
     trasc
    0.43
    ostante
    0.42
    știg
    0.40
    ட்டா
    0.40
     Anteil
    0.40
     Achieve
    0.40
    譚
    0.40
    രിക്കുന്നു
    0.40
    Activations Density 0.000%

    No Known Activations