© 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. 247176
    Prev
    Next
    INDEX
    Explanations

    numbers for ranges and lists

    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
     thumbnail
    0.42
     Ampl
    0.42
    栋
    0.39
     ampl
    0.39
     amplification
    0.38
    棟
    0.38
     looks
    0.37
    Ampl
    0.37
     amphithe
    0.37
    தான்
    0.37
    POSITIVE LOGITS
    呛
    0.37
    cticamente
    0.37
     Elite
    0.36
    सेज
    0.36
     Greenwich
    0.35
     проблемой
    0.34
    ibet
    0.34
    اما
    0.34
     Consultancy
    0.34
    郤
    0.33
    Activations Density 0.007%

    No Known Activations