© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 206355
    Prev
    Next
    INDEX
    Explanations

    notebooks and stationery

    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_19_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
     Happiness
    0.16
     happiness
    0.14
     Coupon
    0.14
     affirmation
    0.14
    $>
    0.14
     hippie
    0.14
     bladder
    0.14
     spoons
    0.13
     vars
    0.13
     alkaline
    0.13
    POSITIVE LOGITS
    ieważ
    0.15
    كره
    0.13
    orest
    0.13
    传染
    0.13
    Collision
    0.12
     বেশকিছু
    0.12
    োলার
    0.12
    ினான்
    0.12
    𝐞
    0.12
    onal
    0.12
    Activations Density 0.001%

    No Known Activations