© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10578
    Prev
    Next
    INDEX
    Explanations

    planting or suggestion

    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_13_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
    iasi
    0.59
    arians
    0.55
    ⴰ
    0.54
     έως
    0.53
    hourglass
    0.52
     amateurs
    0.52
    ynia
    0.52
    Ａ
    0.52
    𝗬
    0.52
    alanine
    0.51
    POSITIVE LOGITS
     mind
    0.64
    ل
    0.63
    )(
    0.54
     or
    0.52
     trustworthy
    0.51
    J
    0.50
    ST
    0.50
     Domino
    0.50
    G
    0.50
     her
    0.50
    Activations Density 0.046%

    No Known Activations