© 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. 221098
    Prev
    Next
    INDEX
    Explanations

    want to make you

    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
     thực
    0.33
     भांड
    0.33
     Реа
    0.33
    
    0.32
     Pipeline
    0.31
     Thực
    0.30
     বাস্তব
    0.30
    Dia
    0.30
    辶
    0.30
     humbling
    0.30
    POSITIVE LOGITS
     recommending
    0.32
     gestures
    0.31
     earn
    0.30
     advising
    0.30
     accords
    0.30
    apay
    0.30
     collaborations
    0.29
     RETURNS
    0.29
     wondering
    0.28
     advises
    0.28
    Activations Density 0.006%

    No Known Activations