© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60561
    Prev
    Next
    INDEX
    Explanations

    Drew names

    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_2_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
    ش
    1.80
    ле
    1.61
    ال
    1.52
    ’
    1.47
    ק
    1.47
     I
    1.45
    that
    1.39
    K
    1.36
    ח
    1.30
    ف
    1.30
    POSITIVE LOGITS
    その
    1.16
    ある
    1.00
     electrically
    1.00
    ない
    0.98
     disposizione
    0.96
     percentuale
    0.95
    ה
    0.94
     பகுதி
    0.93
    کر
    0.92
    CIÓN
    0.92
    Activations Density 0.002%

    No Known Activations