© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 252911
    Prev
    Next
    INDEX
    Explanations

    Pro/Pk terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     |
    0.76
     ~~
    0.42
    |
    0.41
     הנו
    0.41
     =~
    0.40
    较低
    0.39
     |\
    0.38
     kuru
    0.37
     ent
    0.37
     \|
    0.36
    POSITIVE LOGITS
    Pro
    0.82
    pro
    0.80
    pk
    0.79
     pk
    0.77
     pro
    0.77
     Pro
    0.77
    Pk
    0.70
    PK
    0.56
     PK
    0.48
    Lens
    0.48
    Activations Density 0.002%

    No Known Activations