© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 207214
    Prev
    Next
    INDEX
    Explanations

    tap

    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_56_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
     tap
    0.88
    tap
    0.78
     T
    0.65
     t
    0.61
     Tap
    0.61
    Tap
    0.61
    ต
    0.56
     Т
    0.55
    Т
    0.54
    t
    0.52
    POSITIVE LOGITS
    estone
    0.40
    esi
    0.40
    estas
    0.40
    esti
    0.38
    etre
    0.38
    ESTER
    0.37
    enite
    0.37
    ester
    0.37
    iata
    0.36
    emark
    0.35
    Activations Density 0.000%

    No Known Activations