© 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. 204447
    Prev
    Next
    INDEX
    Explanations

    worsening progression

    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
    bukti
    0.41
    arantad
    0.38
    woods
    0.35
    ueta
    0.35
    布団
    0.34
    %!
    0.34
    utia
    0.34
    Ọ
    0.33
    Div
    0.33
    ドド
    0.33
    POSITIVE LOGITS
     increasing
    0.77
     growing
    0.66
    increasing
    0.65
    Increasing
    0.64
     Increasing
    0.63
     leg
    0.61
     점점
    0.61
     legs
    0.57
     rising
    0.56
     intensifying
    0.56
    Activations Density 0.003%

    No Known Activations