© 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. 35249
    Prev
    Next
    INDEX
    Explanations

    Ken

    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
     Cyborg
    0.41
    irian
    0.40
    亗
    0.39
    Victor
    0.39
     Аб
    0.38
     Iterable
    0.36
     Comptroller
    0.36
     Waalaikumsalam
    0.36
    ὁ
    0.36
    comprom
    0.36
    POSITIVE LOGITS
     Kenny
    0.49
     Kenn
    0.47
    Kenny
    0.47
    Kenn
    0.46
     giác
    0.44
     Rocky
    0.44
     KEN
    0.44
     Ken
    0.43
     Tom
    0.41
     Kenneth
    0.40
    Activations Density 0.003%

    No Known Activations