© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 58429
    Prev
    Next
    INDEX
    Explanations

    names and proper nouns

    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_59_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
    뿅
    0.42
     ó
    0.37
     agrupación
    0.37
    aré
    0.37
    niejsze
    0.36
     зарегистри
    0.35
     yearning
    0.35
     dome
    0.35
     cenu
    0.35
    ამე
    0.35
    POSITIVE LOGITS
     WIN
    0.56
     WJ
    0.49
     f
    0.48
     Block
    0.47
     IT
    0.47
    WIN
    0.46
    Dav
    0.46
     Dav
    0.45
     APRIL
    0.44
     Berry
    0.44
    Activations Density 0.009%

    No Known Activations