© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 200233
    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_50_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
     जलाशय
    0.39
     আবরণ
    0.38
     indietro
    0.38
     stimulants
    0.38
     මො
    0.38
     PRL
    0.38
    ಓ
    0.38
     repositories
    0.37
     odstr
    0.37
     KLE
    0.37
    POSITIVE LOGITS
    циони
    0.36
    <0xE2>
    0.34
    ेक
    0.34
    ANTED
    0.33
    Ī
    0.33
    NOWLED
    0.33
    linger
    0.32
    eev
    0.32
    崴
    0.32
    orah
    0.31
    Activations Density 0.000%

    No Known Activations