© 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. 86239
    Prev
    Next
    INDEX
    Explanations

    events that follow or arise

    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
    ры
    0.86
    า
    0.84
    <0xA3>
    0.81
    ong
    0.81
    <0x80>
    0.79
    you
    0.73
    та
    0.72
    regulating
    0.67
    ут
    0.67
    िओ
    0.66
    POSITIVE LOGITS
    i
    0.66
    \
    0.60
     Analyst
    0.59
     alimenta
    0.59
    ರಣ
    0.58
     collaborators
    0.57
     Einfluss
    0.57
     ships
    0.56
     Peaks
    0.56
     fertilizers
    0.55
    Activations Density 0.015%

    No Known Activations