© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108086
    Prev
    Next
    INDEX
    Explanations

    godot engine

    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
    ↵
    1.48
    '
    1.21
    <0x80>
    1.16
    (
    0.98
    く
    0.96
    ে
    0.96
    ii
    0.92
    ᱴ
    0.89
     práct
    0.88
    ب
    0.88
    POSITIVE LOGITS
     are
    1.66
    2
    1.52
    ных
    1.41
    p
    1.32
    um
    1.29
    v
    1.23
    ні
    1.19
    ری
    1.14
    OD
    1.13
    ના
    1.13
    Activations Density 0.001%

    No Known Activations