© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117557
    Prev
    Next
    INDEX
    Explanations

    introduced

    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_27_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
     "."
    0.38
    okit
    0.37
     очки
    0.37
    quoting
    0.36
    揊
    0.36
    ッジ
    0.36
    途
    0.35
    萤
    0.35
    档
    0.35
    blockquote
    0.34
    POSITIVE LOGITS
     primeiro
    0.49
     crippled
    0.47
     chained
    0.45
     primeira
    0.45
     unforgettable
    0.44
     primeras
    0.42
     helpless
    0.41
     беше
    0.41
     primeiras
    0.41
     første
    0.41
    Activations Density 0.035%

    No Known Activations