© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 5214
    Prev
    Next
    INDEX
    Explanations

    and

    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_44_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
    ionalmente
    0.38
    Maf
    0.37
    ഞ്ചി
    0.36
    iete
    0.36
     Fleurit
    0.35
    `-
    0.35
    charg
    0.34
    hots
    0.34
    auxite
    0.34
    გან
    0.34
    POSITIVE LOGITS
    Zb
    0.37
    Ak
    0.36
     Zb
    0.35
     Fey
    0.35
    AdapterView
    0.34
     Kimball
    0.34
    טל
    0.34
     CA
    0.33
    सवाल
    0.33
    ሽ
    0.33
    Activations Density 0.068%

    No Known Activations