© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 85631
    Prev
    Next
    INDEX
    Explanations

    pizza and related concepts

    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_3_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
    .
    0.76
    :
    0.64
    iel
    0.64
    ann
    0.60
     in
    0.59
    تر
    0.58
    ید
    0.57
    ມັນ
    0.57
    emen
    0.55
     are
    0.55
    POSITIVE LOGITS
    ة
    0.79
    ו
    0.75
    ী
    0.74
    at
    0.68
    ോ
    0.67
    و
    0.66
    า
    0.66
    のは
    0.64
    G
    0.61
    ли
    0.59
    Activations Density 0.001%

    No Known Activations