© 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. 158696
    Prev
    Next
    INDEX
    Explanations

    Instructions and formatting

    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
     egos
    0.42
     aunt
    0.40
     seguramente
    0.35
     ego
    0.34
    ﻘ
    0.34
     Aidan
    0.34
     endless
    0.34
     A
    0.33
     heartbeat
    0.33
     Aiden
    0.33
    POSITIVE LOGITS
    ogène
    0.48
    UILLER
    0.47
     valeur
    0.47
     Musée
    0.47
    Longueur
    0.46
     pouces
    0.46
    रहे
    0.46
     protéines
    0.45
     Royaume
    0.45
    Droite
    0.45
    Activations Density 0.001%

    No Known Activations