© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 36914
    Prev
    Next
    INDEX
    Explanations

    locksmith or lockpicking

    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
    د
    0.73
    。
    0.67
    জ
    0.64
    0.63
     seguir
    0.61
    ח
    0.61
    д
    0.61
    0.59
    دين
    0.58
    ാ
    0.58
    POSITIVE LOGITS
    n
    1.27
    y
    1.02
    r
    0.97
    m
    0.89
    t
    0.85
    s
    0.85
    l
    0.85
    h
    0.83
    1
    0.81
    mə
    0.77
    Activations Density 0.002%

    No Known Activations