© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 3238
    Prev
    Next
    INDEX
    Explanations

    stability, loading plans, practical training, project management

    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_38_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
    휀
    0.40
    }...
    0.39
    藩
    0.39
    見える
    0.38
     Rudolf
    0.37
    leştir
    0.37
     स्क्र
    0.36
     الاب
    0.36
    }}^{*}\
    0.36
     அதிச
    0.35
    POSITIVE LOGITS
     mar
    0.38
    PGS
    0.38
    mar
    0.37
    cador
    0.36
    urches
    0.35
    KM
    0.35
     NSString
    0.35
     организа
    0.34
     perfor
    0.34
    కుల
    0.34
    Activations Density 0.022%

    No Known Activations