© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 16350
    Prev
    Next
    INDEX
    Explanations

    Feature definition or assignment

    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_34_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
     vistos
    0.38
     respected
    0.37
    vertices
    0.37
    ො
    0.36
     కె
    0.36
     vertices
    0.35
     reproduces
    0.34
     wasted
    0.33
     excret
    0.33
    constructed
    0.33
    POSITIVE LOGITS
    兕
    0.42
     Biennale
    0.39
     Antibody
    0.39
    amaran
    0.38
     مارچ
    0.37
     Neutron
    0.37
     Insulation
    0.37
     Nucleaire
    0.36
    栆
    0.36
    .............
    0.36
    Activations Density 0.007%

    No Known Activations