© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 30265
    Prev
    Next
    INDEX
    Explanations

    counting characters or numbers

    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
    ipin
    0.37
    ською
    0.36
    .):
    0.35
    ይ
    0.35
     ground
    0.34
     Rak
    0.34
    بوون
    0.34
     ஜ
    0.33
     PU
    0.33
     Mullen
    0.33
    POSITIVE LOGITS
     разбира
    0.42
    ச்சார
    0.39
    ચાર
    0.37
    Lung
    0.37
    idão
    0.37
    Prox
    0.37
     lung
    0.36
    NDAY
    0.36
    Sunday
    0.36
     sunday
    0.36
    Activations Density 0.011%

    No Known Activations