© 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. 216547
    Prev
    Next
    INDEX
    Explanations

    square root limit in division checks

    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
    足球
    0.44
    zam
    0.41
    chro
    0.40
     எனப்படும்
    0.40
    headless
    0.40
    퐫
    0.40
    sam
    0.40
    എ
    0.39
    cylinder
    0.39
    logout
    0.38
    POSITIVE LOGITS
     possibly
    0.46
     combined
    0.40
    ביר
    0.40
     combine
    0.39
     Combine
    0.39
     session
    0.38
     attributed
    0.38
     deterior
    0.38
     natural
    0.38
     perhaps
    0.38
    Activations Density 0.002%

    No Known Activations