© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158283
    Prev
    Next
    INDEX
    Explanations

    Kármán line

    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_2_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
    d
    2.06
    b
    1.91
    z
    1.80
    ll
    1.64
    t
    1.59
    to
    1.55
    n
    1.52
    y
    1.49
    u
    1.47
    de
    1.39
    POSITIVE LOGITS
    ре
    1.35
    ți
    1.13
    ερμαν
    1.08
    ры
    1.05
    ту
    1.05
    ется
    1.01
    し
    1.00
    ло
    0.98
    aría
    0.96
    이다
    0.95
    Activations Density 0.001%

    No Known Activations