© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 206365
    Prev
    Next
    INDEX
    Explanations

    emergency assistance, frameworks

    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_37_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
    лән
    0.43
     canh
    0.42
    愭
    0.42
     सेंचुरी
    0.41
     khám
    0.41
     nâu
    0.39
     সোশ্যাল
    0.39
     Quân
    0.39
    扔
    0.39
    மைச்சர்
    0.38
    POSITIVE LOGITS
     arbit
    0.87
     arbitration
    0.84
     Arbitration
    0.78
     arbitr
    0.73
     arbitrator
    0.70
     Arbit
    0.70
    arbit
    0.69
    Arbit
    0.69
     Arb
    0.59
     arb
    0.59
    Activations Density 0.000%

    No Known Activations