© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53241
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_30_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
    ἂ
    0.43
    क्लो
    0.38
    prompt
    0.38
     grosseur
    0.37
    ')}>
    0.36
    SpawnEntry
    0.35
    colspan
    0.35
    து
    0.34
    brack
    0.34
    摹
    0.34
    POSITIVE LOGITS
     beauties
    0.45
     glory
    0.44
     glories
    0.42
     ТО
    0.41
     Beautiful
    0.40
     mellitus
    0.39
     Insulin
    0.39
     loi
    0.38
     Updates
    0.38
     watering
    0.37
    Activations Density 0.000%

    No Known Activations