© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134100
    Prev
    Next
    INDEX
    Explanations

    action completed or status determined

    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_37_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
     telah
    1.26
     đã
    1.22
    已
    1.19
    已经
    1.12
    已经被
    1.03
     already
    1.01
    已經
    1.00
    已被
    0.99
     sudah
    0.96
    都已经
    0.94
    POSITIVE LOGITS
    준
    0.38
    ុង
    0.38
    hm
    0.37
    कभी
    0.37
    frak
    0.36
    burden
    0.35
    ----+
    0.34
    綦
    0.34
    hid
    0.33
     itemCount
    0.33
    Activations Density 0.041%

    No Known Activations