© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 198683
    Prev
    Next
    INDEX
    Explanations

    mental conditions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    ARD
    0.41
    আয়
    0.41
     Autoren
    0.41
    Arn
    0.39
     خلي
    0.38
     prioritise
    0.38
    覤
    0.38
     आपूर्ति
    0.37
    aspid
    0.37
     Vinyl
    0.36
    POSITIVE LOGITS
     mental
    0.52
    istic
    0.50
    istique
    0.49
    istes
    0.49
    ism
    0.47
     Mental
    0.47
    τισ
    0.46
    티
    0.46
    主义
    0.45
    iste
    0.44
    Activations Density 0.012%

    No Known Activations