© 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. 176440
    Prev
    Next
    INDEX
    Explanations

    Portland places

    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
    lin
    0.44
     lin
    0.43
    𝗁
    0.42
    林
    0.42
    ớp
    0.41
     садо
    0.40
    榷
    0.40
    πού
    0.40
    衲
    0.38
     dampers
    0.37
    POSITIVE LOGITS
     Ada
    0.51
    Ada
    0.48
    Flare
    0.45
     ADA
    0.42
     গন
    0.42
    Activate
    0.39
     Gordon
    0.38
     cloned
    0.38
     فول
    0.37
    ව
    0.37
    Activations Density 0.000%

    No Known Activations