© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144124
    Prev
    Next
    INDEX
    Explanations

    lyrical

    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_0_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
    ED
    1.84
    IN
    1.60
    EN
    1.59
    AN
    1.50
    AS
    1.49
    IS
    1.42
    Е
    1.40
    ES
    1.39
    AL
    1.35
     I
    1.34
    POSITIVE LOGITS
    '
    2.13
    :
    1.56
    (
    1.55
    ಯ
    1.37
    తో
    1.34
    تها
    1.32
    اي
    1.30
    τε
    1.29
    tedir
    1.27
    。
    1.25
    Activations Density 0.000%

    No Known Activations