© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 201537
    Prev
    Next
    INDEX
    Explanations

    scientific discussions of matter

    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
    и
    0.58
     conceded
    0.55
    ímos
    0.50
     الك
    0.50
    ovali
    0.48
     conceding
    0.46
    čen
    0.46
    кових
    0.46
    錘
    0.46
    ла
    0.46
    POSITIVE LOGITS
    Begin
    0.48
    Stylesheet
    0.45
    Here
    0.45
    !
    0.44
     시작
    0.44
    Gut
    0.44
    Txt
    0.44
    防护
    0.44
    Tiles
    0.42
    PHP
    0.42
    Activations Density 0.000%

    No Known Activations