© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 208363
    Prev
    Next
    INDEX
    Explanations

    shooting or shots

    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_19_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
     wirkt
    0.42
    Ƒ
    0.42
     Chab
    0.42
     tire
    0.41
     شاب
    0.40
     Robb
    0.40
    біт
    0.39
     fetal
    0.39
     बबलू
    0.39
    ebles
    0.39
    POSITIVE LOGITS
     للا
    0.41
    大胆
    0.41
    鎂
    0.41
    蛞
    0.39
     اذا
    0.39
    घु
    0.38
    )~
    0.38
    ention
    0.37
    མ་
    0.37
    ಕು
    0.37
    Activations Density 0.000%

    No Known Activations