© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80338
    Prev
    Next
    INDEX
    Explanations

    redesign

    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_0_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
     меня
    1.29
     in
    1.15
    ！)
    1.13
    }.
    1.10
     οπο
    1.09
    。)
    1.09
    س
    1.08
     في
    1.06
    )：
    1.06
    "')
    1.06
    POSITIVE LOGITS
    ות
    2.28
    ം
    1.94
    ம்
    1.90
    at
    1.84
    ו
    1.71
    i
    1.68
    ం
    1.68
    er
    1.67
    ر
    1.56
    en
    1.55
    Activations Density 0.001%

    No Known Activations