© 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. 111104
    Prev
    Next
    INDEX
    Explanations

    dimensionality

    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
    ス
    1.34
     to
    1.17
    なら
    1.16
     as
    1.14
    は
    1.13
    3
    1.11
    с
    1.11
    กัน
    1.09
     on
    1.09
     FirebaseAuth
    1.07
    POSITIVE LOGITS
    p
    1.83
    n
    1.60
    y
    1.60
    x
    1.54
    en
    1.49
    od
    1.43
    ari
    1.36
    il
    1.34
    b
    1.32
    ir
    1.31
    Activations Density 0.001%

    No Known Activations