© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 137360
    Prev
    Next
    INDEX
    Explanations

    in range

    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_37_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
    Hozz
    0.45
    anchez
    0.41
    óf
    0.40
    嗌
    0.39
    รี
    0.38
    भा
    0.38
     lingers
    0.38
    룰
    0.37
    𐱃
    0.37
    री
    0.37
    POSITIVE LOGITS
     [{'
    0.41
     диапазо
    0.39
     কা
    0.37
     '//
    0.35
    ({'
    0.35
    范围内
    0.35
    ([(
    0.35
     Safety
    0.34
    ']]
    0.34
    ([]
    0.33
    Activations Density 0.002%

    No Known Activations