© 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. 161723
    Prev
    Next
    INDEX
    Explanations

    grocery shopping

    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
     heals
    0.39
    𝑛
    0.37
    씰
    0.37
     bialgebra
    0.36
    🩹
    0.34
    ﹰ
    0.34
     уничто
    0.34
    🇾
    0.34
    ऊंगा
    0.34
    पहरण
    0.33
    POSITIVE LOGITS
     button
    0.34
    ச்சின்ன
    0.34
    GetUser
    0.34
     note
    0.33
     মহার
    0.33
     baked
    0.32
     відпо
    0.32
     talk
    0.32
     electro
    0.31
     laund
    0.31
    Activations Density 0.002%

    No Known Activations