© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58136
    Prev
    Next
    INDEX
    Explanations

    miraculous, biracial, Laracasts

    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_2_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
    ר
    0.60
    ?
    0.55
    Time
    0.54
    いです
    0.54
    。
    0.50
    م
    0.50
    ま
    0.50
    ر
    0.49
    يني
    0.49
     poteva
    0.49
    POSITIVE LOGITS
    )
    0.89
    d
    0.89
     are
    0.81
    ма
    0.71
    h
    0.68
    t
    0.64
    д
    0.64
    c
    0.62
    ü
    0.61
    :
    0.61
    Activations Density 0.000%

    No Known Activations