© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 196549
    Prev
    Next
    INDEX
    Explanations

    archaeological

    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_46_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
    stones
    0.42
     discos
    0.42
     concepto
    0.38
     bones
    0.37
    historic
    0.37
     Historic
    0.37
    Historic
    0.36
    崢
    0.36
    Preliminary
    0.35
    こ
    0.35
    POSITIVE LOGITS
     douce
    0.38
     информа
    0.37
     ABOUT
    0.37
    留
    0.37
     vacío
    0.37
     monet
    0.36
    PhotoMode
    0.36
     biens
    0.36
     चूंकि
    0.36
     kuş
    0.36
    Activations Density 0.001%

    No Known Activations