© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14500
    Prev
    Next
    INDEX
    Explanations

    and

    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_15_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
     Furthermore
    0.51
     Additionally
    0.51
    läufig
    0.51
    r
    0.50
    us
    0.48
    g
    0.48
    cs
    0.48
    sc
    0.48
    ened
    0.47
    js
    0.46
    POSITIVE LOGITS
     llamada
    0.55
    ز
    0.55
    ла
    0.50
    ιν
    0.49
     posibles
    0.49
    ﻓ
    0.49
     حالة
    0.49
     diez
    0.49
    炁
    0.49
     )।
    0.48
    Activations Density 0.085%

    No Known Activations