© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36159
    Prev
    Next
    INDEX
    Explanations

    autonomous driving regions

    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_3_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
    桃園
    0.65
    首先
    0.62
    ה
    0.61
    ఏ
    0.60
    অ
    0.60
    Hidden
    0.59
    2
    0.59
    정도
    0.59
    </em>
    0.58
     größ
    0.58
    POSITIVE LOGITS
    ri
    0.98
    ين
    0.93
    it
    0.92
    ir
    0.87
    p
    0.83
    n
    0.80
    are
    0.80
    is
    0.80
    la
    0.79
     rests
    0.78
    Activations Density 0.001%

    No Known Activations