© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103337
    Prev
    Next
    INDEX
    Explanations

    Photoshop

    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_1_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
    as
    1.36
    ন
    1.34
    There
    1.27
    in
    1.26
    ing
    1.23
    er
    1.23
    That
    1.16
     únicamente
    1.13
    2
    1.13
    It
    1.11
    POSITIVE LOGITS
    리
    1.01
    らの
    1.00
    ע
    0.98
    ીર
    0.96
    ید
    0.95
    ق
    0.95
    ել
    0.95
    なかった
    0.92
    ಿರುವ
    0.91
    ಿರಿ
    0.90
    Activations Density 0.000%

    No Known Activations