© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 232204
    Prev
    Next
    INDEX
    Explanations

    knowledge cutoff dates

    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_32_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
     ചെറിയ
    0.42
    釣
    0.36
    umination
    0.35
     সামান্য
    0.35
     ઘણા
    0.34
    ضرب
    0.33
    spaces
    0.33
     ઝડ
    0.33
     alphabetical
    0.33
     Fläche
    0.33
    POSITIVE LOGITS
     실제로
    0.39
    DeathRecord
    0.38
     quenched
    0.38
     flourished
    0.37
    𝓖
    0.37
     thrived
    0.36
     consolidated
    0.35
    ກະ
    0.35
     intellectually
    0.34
    会让
    0.34
    Activations Density 0.058%

    No Known Activations