© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 129857
    Prev
    Next
    INDEX
    Explanations

    Sephora, Sephirot, number sense

    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_6_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
    ции
    0.78
    ור
    0.70
    ון
    0.62
    ัน
    0.60
     cria
    0.60
    ี
    0.57
     exemples
    0.56
    ]
    0.55
    ва
    0.55
    って
    0.55
    POSITIVE LOGITS
    leri
    0.70
    name
    0.67
    t
    0.63
    da
    0.57
    erende
    0.56
     Kabhi
    0.56
     Dolphins
    0.55
    ität
    0.55
     Elizabethan
    0.55
     Pyongyang
    0.54
    Activations Density 0.000%

    No Known Activations