© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 131667
    Prev
    Next
    INDEX
    Explanations

    thin atmosphere

    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_6_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
    m
    1.08
    d
    1.07
    м
    0.93
    的
    0.93
    пе
    0.92
    ва
    0.89
     angin
    0.89
     earthenware
    0.89
    ди
    0.88
    х
    0.88
    POSITIVE LOGITS
    I
    1.34
    Star
    0.84
    Story
    0.82
    ißler
    0.82
     बताया
    0.78
    Staff
    0.78
    Hat
    0.78
    urses
    0.77
    ítás
    0.77
    Histoire
    0.76
    Activations Density 0.002%

    No Known Activations