© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 214200
    Prev
    Next
    INDEX
    Explanations

    the

    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_43_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
    wari
    0.43
    iver
    0.41
    wijk
    0.41
    ुणा
    0.40
    ivores
    0.40
    ೈ
    0.40
     animales
    0.39
    cómo
    0.39
    uhan
    0.39
    aire
    0.39
    POSITIVE LOGITS
     benefit
    0.49
     Benefit
    0.47
    Benefit
    0.42
     AFL
    0.40
     detriment
    0.40
    Ф
    0.38
     AM
    0.38
     benefited
    0.36
     instructional
    0.35
     Boon
    0.35
    Activations Density 0.001%

    No Known Activations