© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 211603
    Prev
    Next
    INDEX
    Explanations

    just realized / remembered / saw / found

    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_19_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
    ﻳ
    0.52
     reveló
    0.46
    ;}
    0.46
     elevados
    0.46
    myX
    0.45
    ल्स
    0.45
     valent
    0.44
     vals
    0.44
    <0xA1>
    0.44
    ेश्च
    0.43
    POSITIVE LOGITS
    ül
    0.48
    uncak
    0.47
    uları
    0.46
    urnama
    0.46
    ular
    0.45
     Некоторые
    0.43
    ungle
    0.43
     городской
    0.42
     Boley
    0.42
     উপলক্ষে
    0.42
    Activations Density 0.001%

    No Known Activations