© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 201029
    Prev
    Next
    INDEX
    Explanations

    safe words

    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
     قوانین
    0.38
    뇌
    0.38
    Cluster
    0.37
    token
    0.37
    agents
    0.37
    leftarrow
    0.36
    স্যার
    0.36
    clust
    0.36
    arrow
    0.36
    Cor
    0.36
    POSITIVE LOGITS
     simplic
    0.46
     thé
    0.44
     appartement
    0.43
     ControllerBase
    0.42
     motels
    0.41
    땡
    0.40
     dî
    0.40
     butter
    0.38
     phil
    0.38
     motel
    0.38
    Activations Density 0.006%

    No Known Activations