© 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. 206353
    Prev
    Next
    INDEX
    Explanations

    electron-hole pairs

    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
    (
    0.46
    σε
    0.43
    /
    0.42
     economist
    0.42
     փ
    0.40
     A
    0.40
    پن
    0.40
     Ά
    0.40
    ξ
    0.39
    <i>
    0.39
    POSITIVE LOGITS
     அடிக்கடி
    0.54
    ፈላጊ
    0.51
     የሆነ
    0.49
     выступления
    0.46
    傾向
    0.45
     genellikle
    0.43
     ständig
    0.43
     파인더
    0.43
    難
    0.43
     seekers
    0.43
    Activations Density 0.000%

    No Known Activations