© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83972
    Prev
    Next
    INDEX
    Explanations

    problem: deprivation, isosafrole, view, think

    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_0_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
     i
    0.46
     t
    0.43
     Зо
    0.42
     b
    0.42
     e
    0.42
     Correlation
    0.40
     y
    0.40
    ution
    0.39
     f
    0.39
    হ
    0.39
    POSITIVE LOGITS
     kleinen
    0.56
     uncle
    0.55
     submarines
    0.55
     liquides
    0.54
    labs
    0.52
     aldehydes
    0.52
     humaines
    0.50
    iszt
    0.50
     testaceis
    0.50
     небольшой
    0.50
    Activations Density 0.000%

    No Known Activations