© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 178548
    Prev
    Next
    INDEX
    Explanations

    is called

    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_24_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
     있기
    0.43
     яе
    0.42
    ᅣ
    0.41
    𝙜
    0.40
    ћа
    0.39
    цкі
    0.39
     ڪر
    0.38
     !_
    0.38
    𝖊
    0.38
    ዐ
    0.37
    POSITIVE LOGITS
     Amazon
    0.47
     छान
    0.47
    amazon
    0.41
    inv
    0.40
     Vertical
    0.40
    omatic
    0.39
    Amazon
    0.39
     Freund
    0.39
     Care
    0.39
     Agora
    0.39
    Activations Density 0.000%

    No Known Activations