© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246230
    Prev
    Next
    INDEX
    Explanations

    spacy, en, sr, speech 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
     kaam
    0.43
     Aś
    0.40
    uttle
    0.39
    ॉज
    0.39
     aas
    0.38
    IMS
    0.38
     åp
    0.38
    鳟
    0.38
    ça
    0.37
    asparagus
    0.37
    POSITIVE LOGITS
    loaders
    0.39
     хо
    0.38
     multi
    0.37
     เรียน
    0.36
    マルチ
    0.36
     loaders
    0.36
     multid
    0.36
    ersonic
    0.36
     Pinto
    0.35
     Ho
    0.35
    Activations Density 0.002%

    No Known Activations