© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 201450
    Prev
    Next
    INDEX
    Explanations

    I

    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_46_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
    vie
    0.40
    னால்
    0.40
     presenter
    0.40
    ⃘
    0.40
     представ
    0.39
     dispos
    0.39
    மன்
    0.38
     presentan
    0.38
     begun
    0.37
     ditetapkan
    0.37
    POSITIVE LOGITS
    enció
    0.42
     ام
    0.38
     am
    0.36
    дии
    0.36
     आर्मी
    0.35
    icill
    0.34
     corri
    0.34
    ﻵ
    0.34
    eiro
    0.34
     Voir
    0.33
    Activations Density 0.003%

    No Known Activations