© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 62588
    Prev
    Next
    INDEX
    Explanations

    notte

    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_2_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
    లో
    1.37
    తో
    1.33
    ა
    1.25
    મ
    1.22
    नंतर
    1.10
     at
    0.98
     proporciona
    0.95
    zysz
    0.94
     stanie
    0.92
     bedste
    0.92
    POSITIVE LOGITS
    。
    1.13
    :
    1.11
    {
    1.09
    ue
    1.06
    ।
    1.00
    ati
    0.98
    াত
    0.97
    )。
    0.93
    ott
    0.89
    ,
    0.89
    Activations Density 0.001%

    No Known Activations