© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36197
    Prev
    Next
    INDEX
    Explanations

    option labels

    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_31_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
     Instinct
    0.35
     وذلك
    0.30
     instinct
    0.29
     Joaquin
    0.28
    originals
    0.28
     கூடாது
    0.28
    kenalkan
    0.28
    ̛
    0.28
    achim
    0.27
    訢
    0.27
    POSITIVE LOGITS
     academ
    0.36
     হয়ে
    0.34
    ौड़
    0.32
     आलू
    0.32
     resolution
    0.31
     potatoes
    0.31
     willow
    0.29
     আলু
    0.29
     lamb
    0.29
    rafi
    0.29
    Activations Density 0.001%

    No Known Activations