© 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. 205236
    Prev
    Next
    INDEX
    Explanations

    nausea

    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
     arbitrary
    0.45
     improv
    0.44
    arbit
    0.40
     arbitrarily
    0.38
    ovní
    0.37
     চূড়ান্ত
    0.37
    ્ન
    0.37
    鷳
    0.37
    fp
    0.37
    ર્સ
    0.37
    POSITIVE LOGITS
    แล
    0.49
     ph
    0.47
     j
    0.45
     แล
    0.38
    visional
    0.38
     밀
    0.37
     BLO
    0.36
     descend
    0.35
    িয়ায়
    0.35
     MINUTES
    0.35
    Activations Density 0.005%

    No Known Activations