© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 220330
    Prev
    Next
    INDEX
    Explanations

    areas of life

    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_31_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
     architectural
    0.37
     bouts
    0.37
    អំពី
    0.36
    눅
    0.34
     терми
    0.34
    никами
    0.34
     interviewer
    0.34
    密
    0.34
    MBT
    0.33
     insol
    0.33
    POSITIVE LOGITS
    ädchen
    0.41
    life
    0.37
     EVERY
    0.36
    istles
    0.36
     partout
    0.36
    sning
    0.35
     życiu
    0.34
     Every
    0.34
     мало
    0.34
    bron
    0.33
    Activations Density 0.003%

    No Known Activations