© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 204470
    Prev
    Next
    INDEX
    Explanations

    Grow

    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
    𝚓
    0.41
     talla
    0.39
    origin
    0.37
     exempl
    0.37
     происхождения
    0.37
    oppers
    0.36
     croissance
    0.36
     отве
    0.36
    ufs
    0.36
    -"+
    0.35
    POSITIVE LOGITS
    )^{
    0.40
    isbury
    0.40
    secret
    0.38
     सचिव
    0.38
    隨著
    0.38
     nem
    0.37
    monds
    0.37
     कामकाजी
    0.37
    ळे
    0.36
     institute
    0.36
    Activations Density 0.001%

    No Known Activations