© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35343
    Prev
    Next
    INDEX
    Explanations

    aid in, yield loss

    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_11_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
     flaming
    0.59
     concussion
    0.59
     proteomics
    0.59
    蝌
    0.58
     biosphere
    0.57
    枇
    0.57
     തന്നെ
    0.57
    äksi
    0.56
     fireball
    0.56
    酸素
    0.54
    POSITIVE LOGITS
    risch
    0.64
    elta
    0.63
    ré
    0.63
    nels
    0.62
     o
    0.61
    ELLE
    0.59
     例
    0.59
    *
    0.59
     =
    0.58
    SError
    0.58
    Activations Density 0.000%

    No Known Activations