© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 52552
    Prev
    Next
    INDEX
    Explanations

    return result or true

    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_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
    ን
    0.38
    anie
    0.38
    簡単
    0.37
    Visiting
    0.36
    ন
    0.36
    monton
    0.36
     wisatawan
    0.36
    ዎን
    0.36
    amera
    0.35
    子里
    0.35
    POSITIVE LOGITS
     bleaching
    0.39
     parachute
    0.39
     perennial
    0.37
    紆
    0.37
     dictate
    0.36
     defies
    0.36
     indefinite
    0.36
     anticipates
    0.36
     defect
    0.35
     Along
    0.35
    Activations Density 0.001%

    No Known Activations