© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 261929
    Prev
    Next
    INDEX
    Explanations

    elephant ride

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_22_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
     Donnerstag
    0.41
    磪
    0.38
    ীরের
    0.37
    Saturday
    0.37
    сій
    0.37
     வெள்ள
    0.36
     vendredi
    0.36
     Dienstag
    0.36
     возможно
    0.36
    erunner
    0.36
    POSITIVE LOGITS
     「
    0.35
     rese
    0.35
    이에요
    0.35
    。『
    0.34
     xay
    0.34
     '-
    0.33
    『
    0.33
     『
    0.33
     αγο
    0.33
    ?'
    0.32
    Activations Density 0.001%

    No Known Activations