© 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. 138539
    Prev
    Next
    INDEX
    Explanations

    national identity verification

    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
     comfy
    0.38
     tortured
    0.38
     ಮಾಡಿ
    0.38
     친
    0.38
     Chilli
    0.38
    ovod
    0.37
    休闲
    0.37
    Tennessee
    0.37
    uchtung
    0.36
     inteligencia
    0.36
    POSITIVE LOGITS
     Dirac
    0.43
     Government
    0.41
     signature
    0.41
     Dij
    0.41
     Signature
    0.40
    ฎ
    0.39
     Bhos
    0.39
     Minor
    0.38
     signatures
    0.38
    Signature
    0.38
    Activations Density 0.001%

    No Known Activations