© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214400
    Prev
    Next
    INDEX
    Explanations

    taught elementary/introductory

    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_5_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
    ة
    1.36
    EY
    1.25
    ue
    1.22
    0
    1.22
    ב
    1.22
    ה
    1.21
    ه
    1.18
    ین
    1.17
    E
    1.14
    де
    1.10
    POSITIVE LOGITS
     Í
    1.05
    ない
    1.02
     thoſe
    1.02
     thofe
    1.02
    の状態
    0.99
     utilise
    0.98
     symbolize
    0.96
    ূতন
    0.96
    行う
    0.95
     पहाड़
    0.94
    Activations Density 0.000%

    No Known Activations