© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115942
    Prev
    Next
    INDEX
    Explanations

    parameter options or lists

    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_27_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
    servers
    0.44
     unfolds
    0.41
     manual
    0.41
     nurses
    0.41
     buses
    0.40
    manual
    0.40
     aliens
    0.40
    </blockquote>
    0.40
     grosso
    0.40
     reservoirs
    0.40
    POSITIVE LOGITS
    ชาย
    0.39
    琬
    0.38
     дел
    0.37
    డు
    0.37
    蔡
    0.37
    Expecting
    0.37
    憧
    0.37
     Kinh
    0.36
     επο
    0.36
    指定
    0.35
    Activations Density 0.001%

    No Known Activations