© 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. 205905
    Prev
    Next
    INDEX
    Explanations

    large numbers

    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
    izhou
    0.39
    getTransforms
    0.37
    一つの
    0.37
    ່ງ
    0.36
    }'],
    0.36
    ?”,
    0.35
    #}
    0.35
    Designs
    0.35
    荷
    0.35
    MQ
    0.34
    POSITIVE LOGITS
     Singleton
    0.38
     Castle
    0.38
     Kill
    0.36
     kill
    0.35
     Gall
    0.35
     Carp
    0.35
     Wall
    0.35
     गैंग
    0.35
    ۔
    0.34
     Ill
    0.34
    Activations Density 0.003%

    No Known Activations