© 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. 200426
    Prev
    Next
    INDEX
    Explanations

    games or films like

    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
    သ
    0.42
    affen
    0.40
    prepare
    0.39
    oke
    0.38
     Schoen
    0.37
    녈
    0.37
    DISABLE
    0.37
    ੍ਹ
    0.37
    中に
    0.37
    Coll
    0.36
    POSITIVE LOGITS
     বাহিরে
    0.47
     released
    0.41
     выпусти
    0.40
     Outside
    0.39
    Ⲟ
    0.38
     outside
    0.38
    ட்டாக
    0.38
     Released
    0.37
     releasing
    0.37
     पिला
    0.37
    Activations Density 0.008%

    No Known Activations