© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 216877
    Prev
    Next
    INDEX
    Explanations

    ship prow

    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_50_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
     reward
    0.44
     ster
    0.43
     Reward
    0.43
    讷
    0.39
     Ster
    0.38
     stern
    0.38
    fte
    0.37
     അന
    0.37
     शर्म
    0.37
     tee
    0.37
    POSITIVE LOGITS
     prow
    0.77
     prou
    0.66
     pro
    0.63
     PRO
    0.61
    Pro
    0.59
     Prou
    0.59
     પ્રો
    0.58
     P
    0.58
    PRO
    0.57
     Prov
    0.57
    Activations Density 0.000%

    No Known Activations