© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41383
    Prev
    Next
    INDEX
    Explanations

    IMMEDIATE RELEASE

    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
    )(-
    0.47
    Anche
    0.44
     degeneration
    0.44
    褸
    0.44
    かもしれませんが
    0.43
     karl
    0.43
    ཧ
    0.43
     fertilisers
    0.43
     nihil
    0.42
     fertiliser
    0.42
    POSITIVE LOGITS
    mu
    0.43
     ऊ
    0.41
    classify
    0.41
     Configure
    0.41
    enumerate
    0.40
     relative
    0.38
     من
    0.38
     முருக
    0.38
    му
    0.38
    iva
    0.38
    Activations Density 0.000%

    No Known Activations