© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 198854
    Prev
    Next
    INDEX
    Explanations

    buried under; drowning in

    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_12_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
    si
    0.23
    ti
    0.21
    а
    0.21
    ni
    0.21
    Loved
    0.21
     .
    0.21
    sa
    0.21
    命
    0.21
    і
    0.21
    لام
    0.20
    POSITIVE LOGITS
     වෙ
    0.27
    inicial
    0.27
     Quân
    0.26
    اديه
    0.25
    гают
    0.24
     этими
    0.23
     сразу
    0.23
     mobilize
    0.23
     riesce
    0.23
     වූ
    0.23
    Activations Density 0.000%

    No Known Activations