© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 204568
    Prev
    Next
    INDEX
    Explanations

    What is a

    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_25_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
    ອດ
    0.38
    xsd
    0.37
    ++){
    0.36
     revolving
    0.36
    pra
    0.36
    ãos
    0.35
    なくなる
    0.34
     digress
    0.34
     numerous
    0.34
    ':
    0.33
    POSITIVE LOGITS
     Would
    0.45
     εμφ
    0.44
    零件
    0.42
     Partly
    0.39
    Would
    0.39
     टेक्नोलॉजी
    0.39
     tjän
    0.39
     DISPLAYSURF
    0.38
    焜
    0.38
     εικό
    0.38
    Activations Density 0.015%

    No Known Activations