© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 149384
    Prev
    Next
    INDEX
    Explanations

    say "p" words

    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_59_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
     बँक
    0.49
     voter
    0.48
     bank
    0.47
    Ͻ
    0.43
     बैंक
    0.43
     банк
    0.43
     Voter
    0.42
     utilisateur
    0.39
    ϭ
    0.38
     मतदाता
    0.38
    POSITIVE LOGITS
    Part
    1.23
     part
    1.20
     Part
    1.19
    part
    0.93
     PART
    0.89
    PART
    0.82
     पार्ट
    0.68
     teams
    0.60
     groups
    0.57
    Teams
    0.57
    Activations Density 0.002%

    No Known Activations