© 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. 108457
    Prev
    Next
    INDEX
    Explanations

    EUV lithography

    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
    I
    2.48
    P
    1.46
    R
    1.36
    E
    1.32
    W
    1.32
    A
    1.30
     I
    1.27
    U
    1.23
    B
    1.22
    D
    1.21
    POSITIVE LOGITS
    на
    1.48
    ↵
    1.45
    ل
    1.45
    લ
    1.41
    ל
    1.38
    ת
    1.36
    ين
    1.30
    л
    1.28
    ر
    1.24
    ם
    1.23
    Activations Density 0.000%

    No Known Activations