© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53742
    Prev
    Next
    INDEX
    Explanations

    Ben

    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_55_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
    ᆭ
    0.36
    فانه
    0.36
    谩
    0.35
    ස්
    0.32
    韮
    0.32
    ombr
    0.31
    exercice
    0.31
    辙
    0.31
    छि
    0.31
    aundice
    0.31
    POSITIVE LOGITS
    Ben
    3.67
     Ben
    3.59
     ben
    3.58
     BEN
    3.31
    ben
    3.30
    BEN
    3.22
     Бен
    3.19
    ベン
    2.98
     бен
    2.97
     بن
    2.86
    Activations Density 0.000%

    No Known Activations