© 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
    2. Gemma-3-27B-IT
    3. 6-GEMMASCOPE-2-TRANSCODER-262K
    4. 231354
    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_6_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
    ного
    0.57
    ன்
    0.52
    inę
    0.51
    ных
    0.49
    <0xBB>
    0.49
    <0x80>
    0.48
    ro
    0.48
    нено
    0.47
    िनी
    0.47
    ियों
    0.47
    POSITIVE LOGITS
    of
    0.72
     on
    0.63
     to
    0.62
    كان
    0.57
     for
    0.55
     إ
    0.55
    Package
    0.54
     },
    0.53
    th
    0.52
     zu
    0.52
    Activations Density 0.000%

    No Known Activations