© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120775
    Prev
    Next
    INDEX
    Explanations

    derived

    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_27_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
    คำ
    0.43
     bellow
    0.43
     nej
    0.42
    ại
    0.40
     midi
    0.39
     aerobic
    0.39
    เด
    0.38
    残
    0.35
     intention
    0.35
    น้ำ
    0.34
    POSITIVE LOGITS
     Filipino
    0.73
     Philippine
    0.71
     Filipinos
    0.68
     Philippines
    0.67
    菲律
    0.66
    ₱
    0.66
     Cebu
    0.65
     Bonifacio
    0.64
     Makati
    0.64
    Philippines
    0.63
    Activations Density 0.000%

    No Known Activations