© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 129309
    Prev
    Next
    INDEX
    Explanations

    time on

    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
    are
    0.88
     perils
    0.84
    お金
    0.81
    였
    0.79
     nests
    0.76
    お
    0.75
    зе
    0.72
    isim
    0.72
    ാരി
    0.71
    iters
    0.71
    POSITIVE LOGITS
    (
    1.22
    {
    1.18
    ną
    0.95
    derdag
    0.90
    this
    0.89
    nın
    0.86
    national
    0.86
    ní
    0.84
    ígeno
    0.84
     ט
    0.83
    Activations Density 0.002%

    No Known Activations