© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 159165
    Prev
    Next
    INDEX
    Explanations

    area of a rectangle

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    RING
    0.44
     February
    0.41
     három
    0.39
    Dé
    0.38
    ʀ
    0.38
    DAVID
    0.37
    ارين
    0.37
     dört
    0.36
    汾
    0.36
    ❒
    0.35
    POSITIVE LOGITS
     bois
    0.41
    ః
    0.41
     කොට
    0.39
    igslist
    0.39
     salt
    0.38
     discrep
    0.38
    cula
    0.37
    ണ്ണി
    0.37
    ula
    0.37
     মৃ
    0.37
    Activations Density 0.003%

    No Known Activations