© 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. 203051
    Prev
    Next
    INDEX
    Explanations

    expecting

    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
     for
    1.02
    ی
    0.96
    ス
    0.96
     temu
    0.94
    s
    0.93
     stadium
    0.88
     grayscale
    0.85
     i
    0.85
     luminosity
    0.84
     phasor
    0.84
    POSITIVE LOGITS
    ’
    1.41
    -
    1.13
    Road
    1.04
    Health
    1.01
    l
    0.96
    Plane
    0.94
    ا
    0.93
    Planet
    0.93
    _
    0.93
    Mod
    0.92
    Activations Density 0.001%

    No Known Activations