© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197990
    Prev
    Next
    INDEX
    Explanations

    conversational structure markers

    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_4_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
    etime
    0.59
    os
    0.55
    on
    0.54
     Change
    0.54
     contemplation
    0.52
    per
    0.51
    o
    0.51
    val
    0.50
     régime
    0.50
     dirt
    0.50
    POSITIVE LOGITS
    Leonard
    0.48
    يش
    0.48
     لیګ
    0.48
    يث
    0.46
    (.*
    0.45
    (;
    0.45
    igheid
    0.45
    数字
    0.44
    رق
    0.44
     besonderen
    0.44
    Activations Density 0.000%

    No Known Activations