© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 210623
    Prev
    Next
    INDEX
    Explanations

    tutoring

    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_43_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
     dharm
    0.45
    シオ
    0.41
    ClientID
    0.40
     चंडीगढ़
    0.40
     sedimentary
    0.38
    侪
    0.38
     умира
    0.38
     ghar
    0.37
     대한민국
    0.37
     Gandh
    0.37
    POSITIVE LOGITS
    教
    0.47
    Bond
    0.44
    CE
    0.43
    biggr
    0.42
    rite
    0.40
     CE
    0.40
    Measuring
    0.39
    OOSE
    0.39
    MEAS
    0.38
    Opportunity
    0.38
    Activations Density 0.000%

    No Known Activations