© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75959
    Prev
    Next
    INDEX
    Explanations

    Swift code and jokes

    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_31_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
     슬
    0.41
     slab
    0.40
    Alloc
    0.40
    Allocate
    0.40
     ത
    0.39
     בז
    0.39
    FullName
    0.37
    ឲ
    0.37
    赞
    0.37
     fame
    0.36
    POSITIVE LOGITS
    itaria
    0.38
    iddy
    0.38
    ega
    0.37
    ennis
    0.36
     یعنی
    0.36
     Beled
    0.36
    osaic
    0.35
     म्हणजेच
    0.35
    ettings
    0.35
    മാണ്
    0.35
    Activations Density 0.000%

    No Known Activations