© 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. 203011
    Prev
    Next
    INDEX
    Explanations

    Spanish

    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
     OS
    0.45
    Yam
    0.45
    yam
    0.44
    suz
    0.42
    dul
    0.41
    luğ
    0.41
    /;
    0.40
    人了
    0.40
     Yam
    0.38
    OS
    0.37
    POSITIVE LOGITS
     Going
    0.42
     going
    0.42
     go
    0.40
     gone
    0.39
     soc
    0.39
     G
    0.39
     رفته
    0.39
     Soho
    0.39
     Dap
    0.38
     stakes
    0.38
    Activations Density 0.000%

    No Known Activations