© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214623
    Prev
    Next
    INDEX
    Explanations

    sightseeing

    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_5_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
    in
    1.46
    is
    1.29
    지
    1.24
    el
    1.14
    ام
    1.11
    has
    1.06
    to
    1.05
    midd
    1.02
    Khokhlov
    1.00
    at
    0.99
    POSITIVE LOGITS
    ре
    1.32
    ä
    1.27
    ing
    1.15
    ă
    1.05
    з
    1.01
    ة
    1.01
    ताओं
    1.00
    ется
    0.99
     ì
    0.98
     investigación
    0.97
    Activations Density 0.000%

    No Known Activations