© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14665
    Prev
    Next
    INDEX
    Explanations

    internal controls

    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
     ਨ
    0.60
     нацыяна
    0.56
    보
    0.55
     নাম
    0.52
    ނ
    0.52
     sylvis
    0.51
     viscoelastic
    0.51
     보
    0.50
     پاکستان
    0.50
    timezone
    0.49
    POSITIVE LOGITS
     &
    0.54
    :
    0.50
    emene
    0.46
    াধিক
    0.46
     editar
    0.45
     setCount
    0.44
    arya
    0.44
    ercise
    0.44
    &
    0.44
    ột
    0.42
    Activations Density 0.011%

    No Known Activations