© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 89907
    Prev
    Next
    INDEX
    Explanations

    meridians

    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_60_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
    iveness
    0.44
    icle
    0.36
     contradictions
    0.35
     sil
    0.35
    lau
    0.35
     lL
    0.34
    bl
    0.34
    ޮ
    0.33
    theria
    0.33
    cloudinary
    0.33
    POSITIVE LOGITS
     경
    2.84
    경
    2.69
    经
    2.53
    経
    2.44
    經
    2.41
     kinh
    2.31
     Kinh
    2.23
     Jing
    1.70
    경상
    1.63
    jing
    1.55
    Activations Density 0.011%

    No Known Activations