© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 234154
    Prev
    Next
    INDEX
    Explanations

    "reckon" speech

    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_46_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
    ەیە
    0.38
     বজ্র
    0.36
    Optimal
    0.36
    |.|
    0.36
     optimally
    0.36
     Tuy
    0.35
     አስፈላጊ
    0.35
    isak
    0.35
     शासन
    0.35
     요
    0.34
    POSITIVE LOGITS
     mighty
    0.67
     folks
    0.61
     reckon
    0.54
     Folks
    0.53
     Mighty
    0.49
     reckoned
    0.45
     hank
    0.44
     reckoning
    0.44
     fol
    0.43
    urned
    0.43
    Activations Density 0.006%

    No Known Activations