© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 206433
    Prev
    Next
    INDEX
    Explanations

    duration units like h, d, m, y

    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_25_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
     aerodynamic
    0.42
     Transfers
    0.42
     jurul
    0.42
     transf
    0.41
     thermoplastics
    0.40
     forest
    0.40
     ተ
    0.40
    Transfer
    0.39
     crumbling
    0.39
    Leg
    0.38
    POSITIVE LOGITS
    spanning
    0.37
    veyard
    0.37
     Davis
    0.36
    ls
    0.35
     Database
    0.35
    $\--
    0.34
     jornadas
    0.34
     ejemplos
    0.34
    塗り
    0.34
    lstm
    0.33
    Activations Density 0.001%

    No Known Activations