© 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. 31478
    Prev
    Next
    INDEX
    Explanations

    Am 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_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
    啁
    0.42
     soude
    0.40
    ंध्र
    0.39
     takers
    0.38
    jt
    0.38
    achd
    0.37
     Dhaka
    0.37
    tego
    0.37
    odz
    0.37
     ataxia
    0.36
    POSITIVE LOGITS
    Am
    0.55
    ام
    0.46
     Am
    0.44
    ам
    0.42
    crystal
    0.42
    암
    0.41
     암
    0.40
    Freeman
    0.39
     ам
    0.39
    amyl
    0.39
    Activations Density 0.002%

    No Known Activations