© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50523
    Prev
    Next
    INDEX
    Explanations

    text or image descriptions

    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_31_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
    orato
    0.39
    manuel
    0.36
    Lucas
    0.35
    枼
    0.35
    ancell
    0.34
    ensibility
    0.34
    amos
    0.34
     distribut
    0.34
    ʾ
    0.33
    ronic
    0.33
    POSITIVE LOGITS
     paragraph
    0.55
     footnotes
    0.55
     captions
    0.53
     headings
    0.53
     caption
    0.51
     paragraphs
    0.47
     heading
    0.47
     fields
    0.44
     subheading
    0.44
     그림
    0.43
    Activations Density 0.076%

    No Known Activations