© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36196
    Prev
    Next
    INDEX
    Explanations

    space objects, telescopes, industry, weather, systems

    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
    ч
    0.79
    ين
    0.76
    ى
    0.70
    position
    0.68
    ж
    0.67
    ள்
    0.66
    يل
    0.66
    者
    0.66
    ngày
    0.61
    状態
    0.61
    POSITIVE LOGITS
    '
    0.69
    क
    0.64
     ส
    0.63
     pengurangan
    0.61
     nul
    0.61
     Seagate
    0.61
    nostic
    0.61
    imde
    0.60
     microSD
    0.59
    ouni
    0.59
    Activations Density 0.010%

    No Known Activations