© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39418
    Prev
    Next
    INDEX
    Explanations

    multi-lingual text separators

    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_3_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
    aurants
    0.78
    lenen
    0.75
     toilets
    0.67
    IR
    0.66
     hives
    0.65
     c
    0.64
     this
    0.64
    IC
    0.64
    ется
    0.64
    ट्यूब
    0.64
    POSITIVE LOGITS
    h
    0.83
    t
    0.82
    j
    0.70
    v
    0.67
    o
    0.63
    3
    0.60
     округа
    0.59
    "),
    0.59
    ৩
    0.59
    and
    0.58
    Activations Density 0.001%

    No Known Activations