© 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. 8913
    Prev
    Next
    INDEX
    Explanations

    counting and number recognition

    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
    Ticks
    0.45
    woff
    0.38
    lp
    0.37
    min
    0.37
     positiva
    0.37
    ticks
    0.37
    胛
    0.37
     tick
    0.36
     positive
    0.36
    虱
    0.36
    POSITIVE LOGITS
     izol
    0.39
     எது
    0.39
     گئی
    0.37
    運
    0.37
    ತ್ತು
    0.36
    getAddress
    0.35
     Nasser
    0.35
    resso
    0.35
     identificar
    0.35
     Druck
    0.35
    Activations Density 0.016%

    No Known Activations