© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 179825
    Prev
    Next
    INDEX
    Explanations

    Parameter definitions

    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_24_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
    UserDefaults
    0.23
     автоматы
    0.23
    قتها
    0.23
    ijnlijk
    0.22
    呿
    0.21
    okeh
    0.21
    चालित
    0.20
     Honorary
    0.20
     чыга
    0.20
    ITO
    0.19
    POSITIVE LOGITS
     restoring
    0.22
     restore
    0.22
     restores
    0.21
     transcendence
    0.21
    復
    0.21
    Restore
    0.20
     transcends
    0.20
     surprise
    0.20
     transcendent
    0.20
     variable
    0.20
    Activations Density 0.001%

    No Known Activations