© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97046
    Prev
    Next
    INDEX
    Explanations

    physical rights and integrity

    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_14_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
     =,
    0.52
     Prasad
    0.51
    Mun
    0.49
     Poon
    0.48
    nergy
    0.46
     Dhar
    0.46
     Rehman
    0.46
    梘
    0.46
    ”，
    0.46
    seconds
    0.46
    POSITIVE LOGITS
    raient
    0.58
     opulent
    0.55
     startups
    0.53
     deformations
    0.52
     doomed
    0.50
     delectable
    0.50
     cravings
    0.49
     scrapes
    0.49
     itch
    0.49
     llamados
    0.48
    Activations Density 0.000%

    No Known Activations