© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 49805
    Prev
    Next
    INDEX
    Explanations

    easy to follow

    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_10_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
    Webhook
    0.23
    ásticos
    0.22
    য়ের
    0.21
     Yhat
    0.21
    <unused662>
    0.21
    য়
    0.21
    ताओं
    0.20
    ంగ్
    0.20
    曌
    0.20
    newParameter
    0.20
    POSITIVE LOGITS
     {
    0.25
    ing
    0.24
    le
    0.24
     for
    0.24
     cake
    0.23
    el
    0.23
     dance
    0.23
     similit
    0.23
    sembling
    0.23
     diplomatic
    0.23
    Activations Density 0.024%

    No Known Activations