© 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. 206355
    Prev
    Next
    INDEX
    Explanations

    hypothetical or speculation

    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
     സ്ഥ
    0.43
     स्थान
    0.40
     }]
    0.38
     今天
    0.38
    Complete
    0.37
    取得了
    0.37
     place
    0.37
    يلة
    0.37
    لز
    0.37
    OGLE
    0.36
    POSITIVE LOGITS
     o
    0.91
     O
    0.69
     о
    0.65
     ا
    0.56
     ओ
    0.51
     ο
    0.49
     dis
    0.49
     gonna
    0.45
    O
    0.44
    dis
    0.43
    Activations Density 0.001%

    No Known Activations