© 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. 1265
    Prev
    Next
    INDEX
    Explanations

    Malakas typhoon, mink, East Asia, Africa

    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
    Literature
    0.44
    ema
    0.39
     Cartagena
    0.38
    ించ
    0.37
    㽛
    0.36
    emir
    0.36
    ሚያ
    0.36
    砶
    0.36
     ষ
    0.35
    पांच
    0.35
    POSITIVE LOGITS
     Dekker
    0.40
     fant
    0.40
     megap
    0.38
     kinet
    0.37
     soaked
    0.36
     koos
    0.36
     duit
    0.36
     joint
    0.35
     budget
    0.35
     berd
    0.35
    Activations Density 0.037%

    No Known Activations