© 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. 38390
    Prev
    Next
    INDEX
    Explanations

    rise time

    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
    는
    0.22
     in
    0.21
    ่
    0.21
     by
    0.20
     cont
    0.20
    ك
    0.20
    は
    0.20
     In
    0.20
    ă
    0.19
    દ
    0.19
    POSITIVE LOGITS
    ти
    0.21
     வால்பேப்ப
    0.19
    toothpaste
    0.19
    AGING
    0.18
     तिवारी
    0.18
    Bau
    0.18
     Wav
    0.18
     möglich
    0.18
    ஷி
    0.18
    тала
    0.18
    Activations Density 0.004%

    No Known Activations