© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169596
    Prev
    Next
    INDEX
    Explanations

    Iran official terms

    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_56_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
     기
    0.96
    기
    0.89
     Cơ
    0.67
     cơ
    0.66
    機構
    0.51
    기의
    0.48
    ギ
    0.45
    기가
    0.43
     機
    0.41
     TREND
    0.41
    POSITIVE LOGITS
     হাজ
    0.39
    iate
    0.38
    awat
    0.36
    Читать
    0.36
    Биография
    0.35
    DIS
    0.35
    Pap
    0.35
    ಂಡ
    0.35
    iat
    0.35
     Pap
    0.35
    Activations Density 0.001%

    No Known Activations