© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193890
    Prev
    Next
    INDEX
    Explanations

    significantly increased public

    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
    纨
    0.41
    hopefully
    0.40
     ক্ষীণ
    0.40
     asynchronously
    0.39
    try
    0.38
    ದಲು
    0.37
    ken
    0.36
     hopefully
    0.36
    嶉
    0.36
     पाल
    0.35
    POSITIVE LOGITS
     score
    0.42
     scores
    0.41
     स्कोर
    0.39
    scores
    0.39
     ties
    0.38
     sign
    0.37
     işaret
    0.37
     desto
    0.36
    prit
    0.35
     plaintiffs
    0.35
    Activations Density 0.001%

    No Known Activations