© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86989
    Prev
    Next
    INDEX
    Explanations

    tissue paper culture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
    an
    0.84
    un
    0.82
    n
    0.75
    i
    0.64
    AN
    0.62
    k
    0.62
    ar
    0.60
    ac
    0.60
    m
    0.59
    g
    0.59
    POSITIVE LOGITS
     internasional
    0.71
    り
    0.71
    یت
    0.70
    نی
    0.70
    ید
    0.68
    ли
    0.66
    ет
    0.62
     internacionales
    0.62
    нг
    0.61
     évolution
    0.61
    Activations Density 0.000%

    No Known Activations