© 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. 7439
    Prev
    Next
    INDEX
    Explanations

    numbers followed by equals

    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
     Teich
    0.35
    ाइब
    0.34
    matics
    0.34
    rophic
    0.34
    掉
    0.34
     Mole
    0.33
     EPS
    0.33
    Translation
    0.33
     انك
    0.33
     mole
    0.33
    POSITIVE LOGITS
     良
    0.41
     interviewer
    0.38
     narrates
    0.37
     relatório
    0.37
    なり
    0.36
     narr
    0.35
    InputValue
    0.35
     value
    0.35
    ❽
    0.35
    PathOf
    0.35
    Activations Density 0.014%

    No Known Activations