© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44812
    Prev
    Next
    INDEX
    Explanations

    eliminated

    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_22_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
    े
    0.44
    CartVO
    0.43
     \%$,
    0.43
    vette
    0.39
     bă
    0.39
    ppies
    0.39
    িকভাবে
    0.38
    諏
    0.38
     içine
    0.36
    ộng
    0.36
    POSITIVE LOGITS
     newspaper
    0.47
     entrance
    0.41
     Kas
    0.40
     copy
    0.40
     জের
    0.40
     Rum
    0.39
     kabel
    0.38
     vstup
    0.38
     Newspaper
    0.38
     xyz
    0.38
    Activations Density 0.001%

    No Known Activations