© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 214168
    Prev
    Next
    INDEX
    Explanations

    ruin bars

    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_47_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
     ton
    0.39
     Voluntary
    0.38
    тости
    0.37
     சுத்த
    0.37
    ibou
    0.37
    🐙
    0.37
    rata
    0.37
    ולם
    0.37
    offsets
    0.37
    тони
    0.36
    POSITIVE LOGITS
    yaar
    0.38
    ANA
    0.38
    hkar
    0.38
    INDER
    0.37
     Neel
    0.36
    {}'.
    0.36
    LH
    0.36
    ALLED
    0.35
    Resistance
    0.35
     Arce
    0.35
    Activations Density 0.013%

    No Known Activations