© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45021
    Prev
    Next
    INDEX
    Explanations

    have access, a, any, knowledge

    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_3_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
    ası
    0.73
    ın
    0.71
     fácil
    0.68
    ті
    0.67
     permiso
    0.66
    ری
    0.66
     społec
    0.65
    の
    0.65
     rusa
    0.65
     trono
    0.64
    POSITIVE LOGITS
    ت
    0.59
     Someone
    0.59
    nent
    0.57
     পলিপ
    0.55
    новни
    0.53
    >
    0.53
    jose
    0.52
    dokter
    0.52
    kej
    0.52
    (.*
    0.52
    Activations Density 0.004%

    No Known Activations