© 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. 175443
    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_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
    λεσ
    0.45
     medición
    0.44
    zenie
    0.43
    活
    0.43
    同
    0.42
    捂
    0.42
    越し
    0.42
    揆
    0.42
     စ
    0.41
     tyd
    0.41
    POSITIVE LOGITS
     citrate
    0.46
    juna
    0.45
    स्टार
    0.44
    rop
    0.43
     enormously
    0.43
     tremendously
    0.43
     molybdenum
    0.42
    सात
    0.42
     hydrogens
    0.42
     molyb
    0.42
    Activations Density 0.000%

    No Known Activations