© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14237
    Prev
    Next
    INDEX
    Explanations

    regional hub, higher education, Supreme Court

    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_40_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
    Latin
    0.46
    pho
    0.44
    Phoenix
    0.42
    Pho
    0.40
    quí
    0.39
    脉
    0.38
    pulse
    0.38
    rom
    0.37
     Latin
    0.37
    ילו
    0.36
    POSITIVE LOGITS
     дов
    0.40
     morphogenesis
    0.39
     equivariant
    0.38
     оте
    0.37
     evenly
    0.36
     Fact
    0.36
    agamanam
    0.36
     Schreiben
    0.36
     AsyncTask
    0.35
    樺
    0.35
    Activations Density 0.003%

    No Known Activations