© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 222971
    Prev
    Next
    INDEX
    Explanations

    odd jobs, oddities, oddly

    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_10_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
    :
    0.96
    :“
    0.70
    なる
    0.59
    <td>
    0.58
    τι
    0.57
     άνθρω
    0.57
    4
    0.57
     thirds
    0.56
    Trap
    0.56
    :</
    0.56
    POSITIVE LOGITS
    t
    0.93
    DA
    0.76
    AF
    0.75
    l
    0.75
    <0x80>
    0.75
    あら
    0.73
    g
    0.73
    야
    0.72
    ool
    0.71
    ngram
    0.71
    Activations Density 0.001%

    No Known Activations