© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 176568
    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_24_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
     surprisingly
    0.43
    誠
    0.36
     Surprisingly
    0.36
     ventures
    0.36
    ന്
    0.36
    伡
    0.35
     Cavalry
    0.35
    surprisingly
    0.35
     eCommerce
    0.35
     brightest
    0.34
    POSITIVE LOGITS
    чними
    0.44
     moduli
    0.43
    ”:
    0.42
     servidores
    0.42
    তল
    0.39
    lığ
    0.39
    ленными
    0.39
     poprzez
    0.38
    字段
    0.38
     রক্ষণ
    0.37
    Activations Density 0.000%

    No Known Activations