© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 2988
    Prev
    Next
    INDEX
    Explanations

    text

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
     Dans
    0.44
     Five
    0.40
    ائز
    0.40
    imdi
    0.39
     finisher
    0.39
     T
    0.38
     alo
    0.38
    অপহরণ
    0.38
     finishers
    0.38
    controls
    0.37
    POSITIVE LOGITS
    તું
    0.43
    萑
    0.42
    vigor
    0.38
     шә
    0.37
    Ivan
    0.37
    <unused84>
    0.36
    Vocabulary
    0.36
    荀
    0.36
    Annie
    0.35
     Karma
    0.35
    Activations Density 0.005%

    No Known Activations