© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35873
    Prev
    Next
    INDEX
    Explanations

    old tales and descriptive adjectives

    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
    ang
    0.87
    ong
    0.82
     .
    0.79
    1
    0.77
    .
    0.75
    acola
    0.66
    ¹.
    0.66
    ene
    0.65
    م
    0.65
    에요
    0.65
    POSITIVE LOGITS
    Pre
    0.62
     ಆದ್ದರಿಂದ
    0.58
    ד
    0.57
     পাঠিয়ে
    0.57
     đo
    0.56
    ড়িত
    0.55
    CLOSED
    0.55
     on
    0.54
    ्तीय
    0.54
     ဖြစ်
    0.54
    Activations Density 0.013%

    No Known Activations