© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143747
    Prev
    Next
    INDEX
    Explanations

    letter j

    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_0_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
    0
    2.42
    8
    1.85
    9
    1.73
    2
    1.69
    5
    1.69
    6
    1.59
    </h2>
    1.59
    4
    1.55
    on
    1.54
    3
    1.49
    POSITIVE LOGITS
    م
    1.77
    y
    1.69
    ج
    1.63
    د
    1.57
    g
    1.56
    m
    1.55
    i
    1.48
    d
    1.42
    it
    1.40
    uk
    1.38
    Activations Density 0.000%

    No Known Activations