© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 57456
    Prev
    Next
    INDEX
    Explanations

    document references

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    akarane
    0.46
    ржа
    0.44
     ])
    0.43
     ]:
    0.43
    :
    0.41
    ೋದ
    0.41
     %@
    0.39
    ]:
    0.39
     يَ
    0.38
     \$
    0.38
    POSITIVE LOGITS
    ;(
    0.59
    ;)
    0.52
    .&
    0.52
    。(
    0.52
    Answer
    0.51
    ,(
    0.51
    .}$
    0.51
    .(
    0.50
    .<
    0.50
    。（
    0.50
    Activations Density 0.001%

    No Known Activations