© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 90225
    Prev
    Next
    INDEX
    Explanations

    legal/official sections

    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
    "
    0.66
    жён
    0.58
     și
    0.58
    Behavior
    0.55
     Behavior
    0.55
     oraș
    0.54
    È
    0.54
    Labor
    0.54
    neighbor
    0.54
    ёр
    0.53
    POSITIVE LOGITS
    on
    0.64
    by
    0.63
    :
    0.57
     അവിടെ
    0.53
     there
    0.52
    !:
    0.52
     هناك
    0.52
     acolo
    0.50
     वहाँ
    0.50
     allí
    0.49
    Activations Density 0.000%

    No Known Activations