© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 54420
    Prev
    Next
    INDEX
    Explanations

    places and descriptors

    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_55_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
    oches
    0.39
     irrigated
    0.37
    彦
    0.36
    Dylan
    0.36
    ologische
    0.36
    lessness
    0.36
     IIS
    0.35
     gilded
    0.35
    бота
    0.35
    ويات
    0.35
    POSITIVE LOGITS
    ﻱ
    0.69
    ﻲ
    0.67
    sti
    0.63
    oni
    0.63
    ি
    0.62
    ویی
    0.61
    eli
    0.61
    LI
    0.60
    noti
    0.60
    ربي
    0.60
    Activations Density 0.025%

    No Known Activations