© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206856
    Prev
    Next
    INDEX
    Explanations

    blackness or zeros

    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_20_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
    الحكم
    0.16
    IndexArray
    0.15
     görü
    0.15
    Ὁ
    0.14
     Té
    0.14
    ේශ
    0.14
     Smoothing
    0.14
     logró
    0.14
    ΕΣ
    0.13
    ₸
    0.13
    POSITIVE LOGITS
    :
    0.13
    devil
    0.13
    Threads
    0.13
    ah
    0.12
    w
    0.12
    Thread
    0.12
    Amen
    0.12
     Marley
    0.12
     amenity
    0.12
    ward
    0.12
    Activations Density 0.002%

    No Known Activations