© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79384
    Prev
    Next
    INDEX
    Explanations

    malay, alam

    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_31_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
     Avoid
    0.29
     brilliance
    0.28
     Schre
    0.28
     convict
    0.27
    到了
    0.27
    칫
    0.26
     brilli
    0.26
     brilliantly
    0.26
     Hemos
    0.26
    成就
    0.26
    POSITIVE LOGITS
    =&
    0.30
     समाचार
    0.29
     stockholders
    0.28
     users
    0.28
    йын
    0.28
     రూ
    0.28
    Americans
    0.28
    )&
    0.27
     participants
    0.27
     contraction
    0.27
    Activations Density 0.022%

    No Known Activations