© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106444
    Prev
    Next
    INDEX
    Explanations

    intenta + infinitive 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_1_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
    、
    1.10
    TA
    1.05
    ى
    0.96
    的确
    0.94
    B
    0.90
    C
    0.90
    ן
    0.89
    س
    0.89
    ור
    0.88
    的速度
    0.86
    POSITIVE LOGITS
    ad
    1.06
    य
    1.04
     pasukan
    0.97
    im
    0.94
    cio
    0.94
    ங்கிணை
    0.91
     pantalla
    0.90
    gr
    0.90
     noto
    0.89
     άνθρω
    0.89
    Activations Density 0.002%

    No Known Activations