© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 137940
    Prev
    Next
    INDEX
    Explanations

    intelligence, communications, security

    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_37_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
     de
    1.15
     де
    0.90
     De
    0.86
    De
    0.81
    de
    0.80
     दे
    0.78
    <0xA4>
    0.75
    Classification
    0.70
    classified
    0.70
     classified
    0.66
    POSITIVE LOGITS
    ጲ
    0.39
     রহমানের
    0.38
     keys
    0.38
     ins
    0.38
     इंस
    0.38
     traversal
    0.38
     ক্যাম্পাস
    0.37
     EMS
    0.37
     EMT
    0.37
     railings
    0.37
    Activations Density 0.008%

    No Known Activations