© 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. 129878
    Prev
    Next
    INDEX
    Explanations

    1.5 oz or 1.5 lbs

    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
    Minister
    0.46
    另一个
    0.43
    britannien
    0.42
    different
    0.42
    ទំនង
    0.42
    Different
    0.42
    另
    0.41
    чі
    0.40
    esehatan
    0.40
    aunque
    0.40
    POSITIVE LOGITS
     suivant
    0.47
     timers
    0.45
     emitters
    0.41
     editions
    0.40
     gong
    0.39
     buffers
    0.38
     groupings
    0.38
     years
    0.38
     times
    0.38
     cone
    0.38
    Activations Density 0.001%

    No Known Activations