© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 385
    Prev
    Next
    INDEX
    Explanations

    as inputs

    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
    億
    0.39
     प्रव
    0.38
    கிழ
    0.38
     паліты
    0.36
     north
    0.35
     boil
    0.35
    ềm
    0.35
     በጥ
    0.35
    星球
    0.35
     ś
    0.35
    POSITIVE LOGITS
     input
    2.11
    input
    1.97
     Input
    1.95
     inputs
    1.94
    Input
    1.89
     Inputs
    1.83
    输入
    1.81
    INPUT
    1.75
    inputs
    1.73
     INPUT
    1.71
    Activations Density 0.032%

    No Known Activations