© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 236676
    Prev
    Next
    INDEX
    Explanations

    as

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     porcent
    0.47
    critical
    0.42
    Sebagai
    0.42
    percent
    0.42
     Sebagai
    0.41
    %"
    0.41
    %+
    0.40
    PERCENT
    0.40
    ป็น
    0.40
    %")
    0.39
    POSITIVE LOGITS
    Subscription
    0.48
    ູບ
    0.44
    Orders
    0.41
     isAuthenticated
    0.40
    Secure
    0.40
    订阅
    0.40
    Papa
    0.39
     manually
    0.38
     constructed
    0.38
     subscribed
    0.38
    Activations Density 0.005%

    No Known Activations