© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5906
    Prev
    Next
    INDEX
    Explanations

    punishment or legal terms

    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_39_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
     functionally
    0.41
     tuber
    0.40
    ավոր
    0.36
     dec
    0.36
    Dek
    0.36
     Exter
    0.35
    _->
    0.35
    வரின்
    0.35
     चीज़
    0.35
     चीज़
    0.34
    POSITIVE LOGITS
    逕
    0.44
     Hals
    0.41
     vide
    0.41
    americana
    0.41
    alleg
    0.40
    先
    0.40
    ]._
    0.40
    vide
    0.40
     apprehend
    0.38
    কাম
    0.38
    Activations Density 0.023%

    No Known Activations