© 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. 205594
    Prev
    Next
    INDEX
    Explanations

    Indonesian names and titles

    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
     σε
    0.96
    etry
    0.87
     آئینے
    0.84
    regated
    0.81
     विश्वास
    0.81
    i
    0.81
    enting
    0.79
    .",
    0.79
     понимаю
    0.78
     في
    0.77
    POSITIVE LOGITS
    ن
    1.57
    ন
    1.29
    न
    1.27
    ב
    1.16
     be
    1.13
     to
    1.09
    장
    1.09
    н
    1.06
    น
    1.06
    تر
    1.05
    Activations Density 0.000%

    No Known Activations