© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13453
    Prev
    Next
    INDEX
    Explanations

    publication titles and headers

    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_40_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
    ライス
    0.41
    ಿರಿ
    0.37
    Submission
    0.36
    rps
    0.36
    FRS
    0.36
     conceptions
    0.35
    언
    0.35
    ルコ
    0.35
    Visit
    0.35
    diagnosis
    0.34
    POSITIVE LOGITS
    uhnya
    0.44
     adentro
    0.41
     Restaurant
    0.39
     Horizontal
    0.38
     moins
    0.38
     रविवार
    0.38
     zond
    0.37
     sunday
    0.36
    ৈত
    0.36
     horizontal
    0.35
    Activations Density 0.015%

    No Known Activations