© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 47059
    Prev
    Next
    INDEX
    Explanations

    knows about `know`

    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_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    nogo
    0.45
    স
    0.43
     Carnival
    0.41
    τσι
    0.41
     Energies
    0.40
     Garnier
    0.40
    ினி
    0.40
    нансо
    0.40
    сал
    0.40
    ส
    0.40
    POSITIVE LOGITS
     rom
    0.47
     других
    0.42
     oth
    0.42
     Andre
    0.40
    ウィ
    0.39
     інших
    0.39
     учё
    0.38
    heds
    0.38
     други
    0.38
    如果有
    0.38
    Activations Density 0.019%

    No Known Activations