© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54475
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_30_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
    dehyde
    0.36
    เกี่ยวกับ
    0.36
     Take
    0.34
     toxin
    0.32
    Take
    0.32
    葚
    0.32
     Sympt
    0.32
     Drought
    0.32
    敔
    0.31
     راہ
    0.31
    POSITIVE LOGITS
     attained
    0.45
     attains
    0.43
     సొ
    0.39
     کہانی
    0.38
     transcribed
    0.36
     controlador
    0.36
     emo
    0.36
     suo
    0.35
    жив
    0.35
     thrilled
    0.35
    Activations Density 0.000%

    No Known Activations