© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5920
    Prev
    Next
    INDEX
    Explanations

    nature

    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
     escrib
    0.42
     அம்ப
    0.40
    挿
    0.38
     Desde
    0.37
    uyente
    0.37
    sir
    0.37
    uyentes
    0.37
    아버지
    0.36
    ถึง
    0.36
     triangulation
    0.36
    POSITIVE LOGITS
    弱
    0.53
     weak
    0.51
    weak
    0.41
     weakness
    0.41
     vulner
    0.39
     Weak
    0.39
    [@
    0.39
    @]
    0.39
    Weak
    0.38
     слабо
    0.38
    Activations Density 0.001%

    No Known Activations