© 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. 82156
    Prev
    Next
    INDEX
    Explanations

    Example

    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
    نامه
    0.44
     Hickey
    0.37
     Hand
    0.37
    hanam
    0.37
    Hc
    0.36
     ទ
    0.36
    الح
    0.35
    হত
    0.35
    ալ
    0.35
    ల్‌
    0.35
    POSITIVE LOGITS
     aHUS
    0.42
     USP
    0.41
    ggio
    0.40
    ющие
    0.39
    ਊ
    0.39
    uš
    0.38
     usp
    0.38
     uzn
    0.38
    ous
    0.38
     उषा
    0.37
    Activations Density 0.006%

    No Known Activations