© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91504
    Prev
    Next
    INDEX
    Explanations

    self-exploration, algorithms, abstracts

    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_3_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
    ).
    0.70
    ية
    0.69
    潦
    0.59
    _
    0.58
    ="
    0.57
    োর
    0.57
     If
    0.56
    لا
    0.56
     Malayalam
    0.56
     Consulte
    0.56
    POSITIVE LOGITS
    ।”
    0.76
     של
    0.72
     ҳам
    0.72
     могут
    0.71
     друг
    0.70
     πολλ
    0.70
     طبیعت
    0.70
     في
    0.69
     یه
    0.68
     вси
    0.68
    Activations Density 0.005%

    No Known Activations