© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 202134
    Prev
    Next
    INDEX
    Explanations

    reserved keywords

    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_37_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
    vant
    0.37
    wohl
    0.37
    पुस्तक
    0.37
    홧
    0.36
     Runde
    0.36
    oiden
    0.36
    簡単な
    0.35
     Rollins
    0.35
    streaming
    0.35
    connect
    0.34
    POSITIVE LOGITS
     proib
    0.46
    禁
    0.45
     prohib
    0.44
     expensive
    0.42
     tercih
    0.41
     hazardous
    0.40
     изго
    0.40
    唐
    0.40
     Prohibition
    0.40
     prohibition
    0.39
    Activations Density 0.004%

    No Known Activations