© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1823
    Prev
    Next
    INDEX
    Explanations

    counting or numbering sequences

    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_40_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
     ফর
    0.41
    chell
    0.37
     jogs
    0.35
     fringilla
    0.35
     va
    0.35
    ieras
    0.34
     environ
    0.34
    冪
    0.34
     illet
    0.34
     Pelt
    0.33
    POSITIVE LOGITS
     counting
    2.84
     counted
    2.67
     count
    2.66
     Counting
    2.61
     counts
    2.58
     countdown
    2.56
    Counting
    2.55
    カウント
    2.55
    counting
    2.47
     Countdown
    2.42
    Activations Density 0.183%

    No Known Activations