© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 78004
    Prev
    Next
    INDEX
    Explanations

    Pacific

    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_53_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
    ポケモン
    0.39
     сельского
    0.39
    LLOW
    0.38
     бил
    0.37
    thyl
    0.37
    ɺ
    0.36
     Gaye
    0.35
    lowski
    0.35
    тельности
    0.35
    ́t
    0.35
    POSITIVE LOGITS
    aż
    0.41
    াবাহ
    0.39
    PHAM
    0.39
    eck
    0.39
    аны
    0.38
     すぎ
    0.38
    ा
    0.38
    amsfonts
    0.37
     sire
    0.37
     png
    0.36
    Activations Density 0.001%

    No Known Activations