© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 154791
    Prev
    Next
    INDEX
    Explanations

    Vertex

    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_60_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
     r
    0.52
     ر
    0.42
     implication
    0.42
     watering
    0.41
     !")
    0.41
     connectivity
    0.40
     adapta
    0.40
    its
    0.40
     adip
    0.40
     m
    0.40
    POSITIVE LOGITS
    AI
    0.65
     AI
    0.61
    A
    0.59
    CI
    0.54
     A
    0.52
     AA
    0.50
    AID
    0.49
     WI
    0.48
    DI
    0.48
    EI
    0.47
    Activations Density 0.003%

    No Known Activations