© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17588
    Prev
    Next
    INDEX
    Explanations

    eyelashes

    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_40_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
     ހ
    0.43
    にっいて
    0.40
    解锁
    0.38
     ઉજ
    0.38
    unctive
    0.36
    irer
    0.36
    ὀ
    0.36
    逈
    0.36
    Nitro
    0.36
     desblo
    0.35
    POSITIVE LOGITS
     eyelashes
    1.23
     lashes
    1.20
     lash
    1.18
     Lash
    1.14
     lashed
    1.06
     eyelash
    1.03
    睫
    1.01
    lashes
    0.95
    lash
    0.88
     false
    0.84
    Activations Density 0.020%

    No Known Activations