© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 78092
    Prev
    Next
    INDEX
    Explanations

    even if you don't

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
     elucid
    0.41
     specimen
    0.41
     elucidate
    0.40
    arqu
    0.39
    इंड
    0.39
    domin
    0.38
     boasting
    0.38
    ("*
    0.37
     sentence
    0.37
    native
    0.36
    POSITIVE LOGITS
     мати
    0.44
     MADE
    0.42
     সঙ্গীত
    0.41
     ATV
    0.40
     Cruiser
    0.40
     बाध्य
    0.39
    Padding
    0.39
    MADE
    0.39
     Made
    0.38
     Pada
    0.38
    Activations Density 0.001%

    No Known Activations