© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 101070
    Prev
    Next
    INDEX
    Explanations

    Linus Tech Tips

    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_16_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
    Dreams
    0.16
     neutralization
    0.15
    残酷
    0.14
    創造
    0.13
    dreams
    0.13
    춤
    0.13
    Dream
    0.13
    蹰
    0.13
     Prozent
    0.13
    elser
    0.13
    POSITIVE LOGITS
     isang
    0.17
     یکی
    0.17
     ایک
    0.17
     iki
    0.17
     uma
    0.16
     simplest
    0.16
     aryl
    0.16
     beanie
    0.16
     foodie
    0.16
    }$;
    0.16
    Activations Density 0.002%

    No Known Activations