© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 118192
    Prev
    Next
    INDEX
    Explanations

    nah or meh

    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_27_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
    冥
    0.37
     PPM
    0.37
    済
    0.36
    规范
    0.35
    าราง
    0.34
    Budd
    0.34
    ຢ
    0.34
    Environ
    0.34
    𝐪
    0.34
    मेड
    0.34
    POSITIVE LOGITS
     porque
    0.43
     verlo
    0.41
     karena
    0.40
     posao
    0.40
     perché
    0.38
     bolje
    0.38
     dalších
    0.38
     too
    0.38
    스트
    0.37
     korzyst
    0.37
    Activations Density 0.000%

    No Known Activations