© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 176962
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     vp
    0.47
    変
    0.46
    vp
    0.44
    ysel
    0.38
     dp
    0.36
     Indira
    0.35
    变
    0.35
    羍
    0.34
     vari
    0.34
    㧿
    0.34
    POSITIVE LOGITS
    ╕
    0.42
    лько
    0.41
     Anxiety
    0.38
     convo
    0.37
     {\
    0.37
    лью
    0.37
    ujo
    0.36
    டிய
    0.36
     anisotropy
    0.36
    SBOM
    0.36
    Activations Density 0.000%

    No Known Activations