© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23606
    Prev
    Next
    INDEX
    Explanations

    sl

    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_56_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
    ==",
    0.39
    стьян
    0.38
    abilit
    0.37
     SCA
    0.37
    しかった
    0.37
    숭
    0.37
    ]+"
    0.36
     Sagan
    0.35
     অভিনয়ের
    0.35
    ರಳ
    0.35
    POSITIVE LOGITS
     sl
    2.89
    sl
    2.11
     Sl
    1.64
    Sl
    1.50
    슬
    1.30
     сла
    1.28
     슬
    1.27
    SL
    0.97
    сла
    0.97
    スラ
    0.97
    Activations Density 0.100%

    No Known Activations