© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14081
    Prev
    Next
    INDEX
    Explanations

    receive chunk data

    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_40_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
     وړاندوینه
    0.27
    霏
    0.26
     зимо
    0.26
    䛊
    0.25
    <unused94>
    0.25
    冬季
    0.25
     зи
    0.25
     ډاونلوډ
    0.24
    rimidin
    0.24
    AutoFocus
    0.24
    POSITIVE LOGITS
     s
    0.30
    giene
    0.28
     rabbit
    0.26
     core
    0.26
     series
    0.25
     states
    0.25
     demanding
    0.24
     envelopes
    0.24
    def
    0.24
    lou
    0.24
    Activations Density 0.000%

    No Known Activations