© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 80418
    Prev
    Next
    INDEX
    Explanations

    say "w" 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_53_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
    ალურ
    0.39
     यर
    0.39
    ៊
    0.38
     thats
    0.38
     alz
    0.37
     escritorio
    0.36
     correo
    0.36
     fugiat
    0.36
    ://
    0.36
    friger
    0.35
    POSITIVE LOGITS
    瑭
    0.38
    withTrashed
    0.38
    ర్థ
    0.37
     Tots
    0.37
    ວ
    0.37
     tah
    0.37
    <0xA6>
    0.36
     steroid
    0.35
     Boeing
    0.35
     wit
    0.35
    Activations Density 0.006%

    No Known Activations