© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171638
    Prev
    Next
    INDEX
    Explanations

    pregnancy and kids

    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_20_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
     LESS
    0.27
    爆
    0.26
     DO
    0.26
     、,
    0.26
    ˘
    0.26
     मतदाता
    0.26
     Example
    0.26
     DEST
    0.26
     መሳሪያ
    0.25
    開始
    0.25
    POSITIVE LOGITS
    adina
    0.30
     apoyo
    0.29
    änz
    0.29
    顗
    0.29
    willReturn
    0.28
    schein
    0.28
    ೀವ
    0.27
     atk
    0.27
    ਗ
    0.27
     ginger
    0.26
    Activations Density 0.000%

    No Known Activations