© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38724
    Prev
    Next
    INDEX
    Explanations

    main content

    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_11_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
    了一
    0.65
    ėjo
    0.61
    ið
    0.61
    weapp
    0.61
    đu
    0.60
    u
    0.59
    eye
    0.58
     ත
    0.58
    いが
    0.58
    ુ
    0.58
    POSITIVE LOGITS
    {
    0.55
     techniques
    0.55
    ]
    0.55
    [
    0.54
     Problem
    0.53
     influences
    0.53
     problem
    0.53
    .:
    0.53
    (
    0.52
     proven
    0.52
    Activations Density 0.006%

    No Known Activations