© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 30245
    Prev
    Next
    INDEX
    Explanations

    counting or ongoing actions

    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
    EDITORIAL
    0.40
     అందుకు
    0.38
    谐
    0.37
     निभाई
    0.37
    getLong
    0.35
    (^
    0.35
    𖤐
    0.34
    lever
    0.34
    |_{
    0.33
    体积
    0.33
    POSITIVE LOGITS
     counting
    1.25
     Counting
    1.13
    counting
    1.09
    Counting
    1.06
     contando
    0.96
     rising
    0.82
     running
    0.82
     talking
    0.82
    running
    0.78
     ticking
    0.78
    Activations Density 0.105%

    No Known Activations