© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 243801
    Prev
    Next
    INDEX
    Explanations

    powerapps

    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
    rieb
    0.36
     flooring
    0.36
     वार्ड
    0.36
    牀
    0.35
     Carpet
    0.34
    ENIDO
    0.33
     carpet
    0.32
     डेफ
    0.32
    முடிய
    0.32
    剋
    0.32
    POSITIVE LOGITS
    Privacy
    0.42
    вой
    0.41
     privacy
    0.36
     Privacy
    0.36
    privacy
    0.36
    Disclaimer
    0.34
    隐私
    0.34
    Notes
    0.34
    дила
    0.34
    ㄨ
    0.33
    Activations Density 0.001%

    No Known Activations