© 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. 133199
    Prev
    Next
    INDEX
    Explanations

    media and names

    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
     Jabal
    0.45
    lvl
    0.43
    jac
    0.42
     буди
    0.38
     Derby
    0.38
    DER
    0.37
    Р
    0.37
    <unused78>
    0.36
     diffused
    0.36
    fw
    0.36
    POSITIVE LOGITS
    Identifiers
    0.41
     Publishers
    0.41
     cardia
    0.41
    atu
    0.39
    Employers
    0.39
    Editor
    0.38
    펍
    0.37
     கிர
    0.37
    ‌.
    0.36
    otu
    0.36
    Activations Density 0.002%

    No Known Activations