© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202069
    Prev
    Next
    INDEX
    Explanations

    art prompts and methods

    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_12_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
    hover
    0.60
     retrato
    0.56
     artistas
    0.56
     hovering
    0.56
     വിൽപ്പന
    0.56
    㐰
    0.56
     awe
    0.55
     personaje
    0.55
     изображения
    0.55
     leftist
    0.55
    POSITIVE LOGITS
    /
    0.62
    </b>
    0.54
     `
    0.48
     والح
    0.48
     TODO
    0.47
    TODO
    0.46
    .}}
    0.46
    ování
    0.45
    rison
    0.45
    Jis
    0.45
    Activations Density 0.007%

    No Known Activations