© 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. 131192
    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
    シ
    0.43
    ِر
    0.42
    ونو
    0.40
    "]},{"
    0.40
     dní
    0.40
     udal
    0.39
     creativity
    0.38
     kasa
    0.37
    ཥ
    0.37
     nô
    0.37
    POSITIVE LOGITS
    els
    0.43
    pec
    0.42
    rees
    0.42
     undertakes
    0.41
    reo
    0.41
    ከላ
    0.41
    Cle
    0.40
     Hollis
    0.40
    ea
    0.40
     wieder
    0.39
    Activations Density 0.000%

    No Known Activations