© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120043
    Prev
    Next
    INDEX
    Explanations

    code tests and declarations

    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_27_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
     Macedonian
    0.40
     Æ
    0.39
     requisite
    0.36
    Æ
    0.36
     sweet
    0.35
     Turkey
    0.35
     Taiwan
    0.35
     Mexico
    0.34
     Quantity
    0.34
     Reclamation
    0.33
    POSITIVE LOGITS
    竰
    0.44
    ច្
    0.42
     bytecode
    0.38
    AutoHide
    0.38
    jboss
    0.37
    尌
    0.36
     simonsen
    0.35
     स्टेन
    0.35
    busters
    0.35
     suppressant
    0.35
    Activations Density 0.002%

    No Known Activations