© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 160684
    Prev
    Next
    INDEX
    Explanations

    Salesforce

    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_2_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
    يد
    1.27
    كس
    1.13
    е
    1.10
    ר
    1.10
     (
    1.06
     Ο
    1.05
    كن
    1.04
     ও
    1.02
     На
    1.01
    anje
    1.01
    POSITIVE LOGITS
    0
    1.52
    to
    1.37
    the
    1.36
    with
    1.02
    2
    1.01
     부터
    0.95
     mikä
    0.95
    𝗯
    0.94
    ０
    0.93
    ز
    0.91
    Activations Density 0.001%

    No Known Activations