© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 236605
    Prev
    Next
    INDEX
    Explanations

    check out these posts

    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_32_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
    POSE
    0.39
    getPopulation
    0.35
    㚣
    0.35
     pleases
    0.34
    omyces
    0.34
    oncé
    0.34
    形態
    0.33
     wager
    0.33
    inare
    0.33
    OSO
    0.33
    POSITIVE LOGITS
    şiv
    0.39
     विवेकानंद
    0.38
     considerato
    0.38
    renc
    0.37
    nemis
    0.37
     ${({
    0.36
     deixe
    0.36
     titulado
    0.36
     culturais
    0.36
     tire
    0.36
    Activations Density 0.000%

    No Known Activations