© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136943
    Prev
    Next
    INDEX
    Explanations

    walking or moving through

    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_12_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
    з
    0.66
     дода
    0.56
     dépasse
    0.54
     prévu
    0.54
     compensated
    0.52
     oversaw
    0.52
     obsług
    0.52
    擔任
    0.52
    𒁳
    0.52
     doesnt
    0.52
    POSITIVE LOGITS
    TP
    0.59
    IT
    0.55
    com
    0.54
    IC
    0.53
    D
    0.53
    ani
    0.52
    protection
    0.52
    orse
    0.50
    molecular
    0.49
    oint
    0.49
    Activations Density 0.001%

    No Known Activations