© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11001
    Prev
    Next
    INDEX
    Explanations

    position or direction

    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_13_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
    த
    0.55
    인
    0.55
     appropriations
    0.51
     postponed
    0.50
     itch
    0.48
    guna
    0.48
     coaster
    0.48
    insurance
    0.48
     tumbuhan
    0.47
    нений
    0.47
    POSITIVE LOGITS
     pud
    0.56
     longitud
    0.55
     :,
    0.52
     }:
    0.51
     النها
    0.50
     describ
    0.48
    ).(
    0.47
     Länge
    0.47
    长度
    0.47
     ".")
    0.46
    Activations Density 0.030%

    No Known Activations