© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 165972
    Prev
    Next
    INDEX
    Explanations

    what models can't

    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_34_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
    耙
    0.43
     decorator
    0.42
    would
    0.42
     previously
    0.40
     would
    0.39
     wouldn
    0.39
     academia
    0.38
    लपुर
    0.37
    previously
    0.37
     WOULD
    0.37
    POSITIVE LOGITS
    Sim
    0.37
    porta
    0.36
    所属
    0.35
    ंक
    0.35
     문의
    0.35
    缟
    0.35
    ataka
    0.35
     भूमि
    0.35
     मिले
    0.34
     Simons
    0.34
    Activations Density 0.004%

    No Known Activations