© 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. 120644
    Prev
    Next
    INDEX
    Explanations

    initiative

    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
    apter
    0.41
    éder
    0.37
     ば
    0.37
    reek
    0.36
    incorporated
    0.36
    ův
    0.36
    yntax
    0.35
     applicationId
    0.35
    уч
    0.35
    invocation
    0.35
    POSITIVE LOGITS
    ێت
    0.41
    ਭ
    0.40
     veine
    0.38
    当店
    0.38
     genus
    0.38
     Ferté
    0.37
     Limestone
    0.37
    LTR
    0.37
     dui
    0.36
     lineWidth
    0.36
    Activations Density 0.002%

    No Known Activations