© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 199674
    Prev
    Next
    INDEX
    Explanations

    1

    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
     antes
    0.40
    ibal
    0.38
     अभिव्यक्ति
    0.37
    ก่อน
    0.37
     قبل
    0.36
    istische
    0.36
    ifra
    0.35
    ্
    0.35
     discovery
    0.35
     before
    0.35
    POSITIVE LOGITS
    𝑍
    0.44
    𝓈
    0.43
     Tö
    0.40
    衵
    0.40
     Герма
    0.40
    ایج
    0.40
     Сі
    0.40
    เซีย
    0.39
     то
    0.37
     मुआव
    0.37
    Activations Density 0.009%

    No Known Activations