© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212377
    Prev
    Next
    INDEX
    Explanations

    further + action verb

    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_5_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
    "
    1.23
    '
    1.17
    6
    1.14
    5
    1.13
    ,
    1.11
     estadísticas
    0.99
    4
    0.94
    وم
    0.94
    8
    0.92
    ৬
    0.92
    POSITIVE LOGITS
    an
    1.66
    ت
    1.48
    ro
    1.41
    it
    1.41
    ר
    1.40
    त
    1.34
    т
    1.34
    the
    1.27
    ת
    1.27
    ق
    1.23
    Activations Density 0.003%

    No Known Activations