© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 33217
    Prev
    Next
    INDEX
    Explanations

    Gate Gourmet

    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
     Half
    0.57
    Half
    0.54
    半
    0.52
     Ord
    0.47
     half
    0.46
    woods
    0.45
     HALF
    0.45
    half
    0.44
     Halb
    0.42
     Bertrand
    0.41
    POSITIVE LOGITS
    媜
    0.42
     dian
    0.40
    玺
    0.39
    maxn
    0.37
    Დ
    0.37
    Texto
    0.37
    当你
    0.37
    ဃ
    0.37
     बेबी
    0.37
     txt
    0.36
    Activations Density 0.000%

    No Known Activations