© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 42328
    Prev
    Next
    INDEX
    Explanations

    code block closing punctuation

    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
     Sorg
    0.53
     Anderson
    0.52
     Sandberg
    0.52
    㖩
    0.52
    坸
    0.50
     Kaufman
    0.49
     Walker
    0.48
    것도
    0.47
     exposureButton
    0.47
    岦
    0.47
    POSITIVE LOGITS
    ="
    0.56
    Happiness
    0.49
    ite
    0.49
     you
    0.48
    dad
    0.47
    nation
    0.46
    ता
    0.45
    दी
    0.45
    Employment
    0.44
    FormField
    0.43
    Activations Density 0.032%

    No Known Activations