© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 176012
    Prev
    Next
    INDEX
    Explanations

    dvd, blu-ray, and CDs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_24_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
     Rein
    0.40
    נו
    0.37
     Omar
    0.37
     reinforcement
    0.37
    腭
    0.36
     racism
    0.36
    Tyler
    0.36
    成了
    0.36
    ექ
    0.36
     transición
    0.35
    POSITIVE LOGITS
     permukaan
    0.43
     ouvido
    0.42
     membeli
    0.41
    ᴜ
    0.41
     hectare
    0.39
     ব্যাঙ্ক
    0.39
     lapangan
    0.39
     Vestone
    0.39
     yattha
    0.39
    क्के
    0.39
    Activations Density 0.000%

    No Known Activations