© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 197771
    Prev
    Next
    INDEX
    Explanations

    group of answer choices

    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
    也有
    0.39
     Road
    0.36
    aulay
    0.36
     PB
    0.35
     également
    0.35
    positivo
    0.35
     low
    0.35
    据
    0.35
     Electric
    0.34
    低
    0.34
    POSITIVE LOGITS
     ਤੁ
    0.40
     agak
    0.40
    धारा
    0.40
     domicile
    0.40
     పరిశ
    0.39
     veranda
    0.39
    obei
    0.38
    見
    0.38
    註
    0.38
    ፈላጊ
    0.37
    Activations Density 0.000%

    No Known Activations