© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 204556
    Prev
    Next
    INDEX
    Explanations

    department

    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_56_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
     en
    0.50
     εν
    0.44
    Encom
    0.43
     En
    0.43
    En
    0.41
     EN
    0.41
    坠
    0.40
    エン
    0.40
     Эн
    0.40
     един
    0.39
    POSITIVE LOGITS
     department
    1.23
    department
    1.16
     depart
    1.12
     Department
    1.08
     departments
    1.08
    Department
    1.05
     Departments
    1.05
     dept
    1.01
    Depart
    0.99
     DEPARTMENT
    0.98
    Activations Density 0.000%

    No Known Activations