© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37781
    Prev
    Next
    INDEX
    Explanations

    boats

    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_57_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
     ur
    0.41
    AllCaps
    0.38
     most
    0.38
    欒
    0.36
    栾
    0.36
     מב
    0.35
    ραι
    0.35
    MILLISE
    0.34
    牵
    0.34
     Cascade
    0.34
    POSITIVE LOGITS
     fol
    0.44
     Fol
    0.43
     boats
    0.42
     hojas
    0.40
    Fol
    0.39
     Planetary
    0.39
    boats
    0.38
     Boats
    0.38
    Ve
    0.37
    のこと
    0.37
    Activations Density 0.000%

    No Known Activations