© 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. 160949
    Prev
    Next
    INDEX
    Explanations

    nomination

    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
    ку
    1.44
     rozwiąz
    1.33
    ной
    1.30
    و
    1.17
    ના
    1.16
    ных
    1.15
     améli
    1.14
    ABOUT
    1.14
    қ
    1.14
     opér
    1.11
    POSITIVE LOGITS
    of
    1.35
    are
    1.27
    er
    1.21
    on
    1.19
    ’
    1.18
    N
    1.16
    K
    1.15
    '
    1.09
    is
    1.02
    ores
    1.02
    Activations Density 0.000%

    No Known Activations