© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 159227
    Prev
    Next
    INDEX
    Explanations

    kala

    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_50_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
    ฉ
    0.75
     छ
    0.70
     CPE
    0.66
     છ
    0.66
     چھ
    0.66
     CPM
    0.64
    छ
    0.64
    ছ
    0.63
     CPS
    0.63
     ছ
    0.59
    POSITIVE LOGITS
     kal
    1.87
    Kal
    1.83
     Kal
    1.81
     KAL
    1.73
     Kala
    1.70
    KAL
    1.69
    kal
    1.67
     Кали
    1.60
     kala
    1.57
    kala
    1.57
    Activations Density 0.001%

    No Known Activations