© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105972
    Prev
    Next
    INDEX
    Explanations

    department names and identifiers

    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_1_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
    بر
    1.15
    いた
    1.15
    した
    1.13
    س
    1.13
    تر
    1.10
    CE
    1.08
    स
    1.06
     it
    1.02
    مل
    1.02
    った
    1.01
    POSITIVE LOGITS
     código
    1.02
    -
    0.93
     proveedor
    0.89
    ↵
    0.87
    0.86
     nuestro
    0.86
     estados
    0.86
    i
    0.85
     by
    0.84
     quienes
    0.83
    Activations Density 0.000%

    No Known Activations