© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 197089
    Prev
    Next
    INDEX
    Explanations

    is

    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_46_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
    Level
    0.40
    GO
    0.39
     level
    0.38
    Beyond
    0.38
    莓
    0.38
    Spider
    0.36
    LEVEL
    0.36
     ܥ
    0.36
    Corner
    0.35
    蔵
    0.35
    POSITIVE LOGITS
     شا
    0.42
    当前
    0.41
    சிரிய
    0.41
     当前
    0.39
     വാഹന
    0.39
     hebben
    0.37
     차량
    0.37
     sidew
    0.37
     Brion
    0.37
     camion
    0.36
    Activations Density 0.007%

    No Known Activations