© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5895
    Prev
    Next
    INDEX
    Explanations

    numbered lists

    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_39_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
     erster
    0.46
    ρκ
    0.43
     первой
    0.43
     első
    0.42
    %)$
    0.39
     ersten
    0.39
     primeira
    0.38
    Ẵ
    0.38
    äub
    0.38
    second
    0.38
    POSITIVE LOGITS
     datasets
    0.41
     Hundreds
    0.39
     COLOR
    0.38
     Sahara
    0.38
    عبير
    0.37
    EVEN
    0.37
     prompted
    0.37
    گم
    0.37
    庸
    0.37
     hundreds
    0.36
    Activations Density 0.047%

    No Known Activations