© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 198037
    Prev
    Next
    INDEX
    Explanations

    past time references like "ago" or "last year"

    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_9_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
    y
    0.98
    in
    0.76
    en
    0.73
    o
    0.73
    x
    0.72
    h
    0.68
    er
    0.68
    u
    0.67
    ai
    0.63
    ag
    0.63
    POSITIVE LOGITS
    드를
    0.55
    ية
    0.51
    스를
    0.47
    ルの
    0.47
    ведения
    0.46
    드의
    0.46
    력이
    0.45
    限于
    0.45
     සමඟ
    0.45
    光学
    0.45
    Activations Density 0.012%

    No Known Activations