© 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. 43341
    Prev
    Next
    INDEX
    Explanations

    character names and game titles

    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
    蛜
    0.55
     مۇ
    0.54
     め
    0.54
    Gosudarstvennyj
    0.53
     ను
    0.52
    help
    0.52
     πολι
    0.51
    𝗱
    0.50
    Ἁ
    0.50
    đi
    0.50
    POSITIVE LOGITS
    }$
    0.65
    لاف
    0.55
     than
    0.49
     trud
    0.48
     عليه
    0.48
     наре
    0.47
    }\
    0.47
     Skinner
    0.46
    身的
    0.46
     Inverse
    0.46
    Activations Density 0.000%

    No Known Activations