© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 168856
    Prev
    Next
    INDEX
    Explanations

    places

    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_56_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
    Pem
    0.41
    markers
    0.39
    ティブ
    0.39
     Markers
    0.38
     Herbert
    0.37
    ompok
    0.37
     erros
    0.36
    哮
    0.36
     പെ
    0.36
    Shroud
    0.36
    POSITIVE LOGITS
     Vans
    0.37
     صلی
    0.36
     LoggerFactory
    0.35
    蝰
    0.34
     Constraint
    0.34
     Applied
    0.34
     Dow
    0.34
     vacuna
    0.34
     BOP
    0.34
     (...)
    0.33
    Activations Density 0.003%

    No Known Activations