© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52148
    Prev
    Next
    INDEX
    Explanations

    code components

    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
     مؤس
    0.35
    HUM
    0.34
    맑
    0.34
     LEGAL
    0.34
     sy
    0.33
    φος
    0.33
    Sang
    0.33
    千年
    0.33
    aacute
    0.32
     Eng
    0.32
    POSITIVE LOGITS
    ⑶
    0.37
    Md
    0.36
     स्टाइल
    0.33
    찮
    0.33
    LinearLayout
    0.33
    ையைப்
    0.33
     kivy
    0.33
     nrow
    0.32
     கேள்
    0.32
     Md
    0.32
    Activations Density 0.000%

    No Known Activations