© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 232885
    Prev
    Next
    INDEX
    Explanations

    Best

    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_46_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
    pract
    0.43
     practice
    0.43
    Pract
    0.41
     Pract
    0.40
     practicing
    0.40
    潟
    0.40
     practically
    0.40
     practitioner
    0.39
     practicar
    0.38
     Practice
    0.38
    POSITIVE LOGITS
    semos
    0.42
     पु
    0.40
    thinkable
    0.39
    铷
    0.38
    sampling
    0.38
    Rub
    0.37
    徫
    0.37
    ಲೋ
    0.37
     Cartagena
    0.37
     sampling
    0.37
    Activations Density 0.001%

    No Known Activations