© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2820
    Prev
    Next
    INDEX
    Explanations

    4-bit quantization

    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_40_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
     Ps
    0.58
    Ps
    0.54
     Bs
    0.52
     Cs
    0.50
    Rs
    0.49
     Ds
    0.47
     Rs
    0.45
     R
    0.45
     Js
    0.43
    Bs
    0.43
    POSITIVE LOGITS
    kve
    0.40
     xuân
    0.39
    holi
    0.38
     hol
    0.37
     होल
    0.36
    ぐ
    0.36
    𝟬
    0.35
    hol
    0.34
    vega
    0.34
     \%
    0.34
    Activations Density 0.035%

    No Known Activations