© 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-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11659
    Prev
    Next
    INDEX
    Explanations

    words from languages other than English, with a bias for French and languages using cyrillic and diacritic marks

    oai_token-act-pair · gemini-2.0-flash

    reflexive pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     desea
    -0.50
    Traceback
    -0.50
    PCell
    -0.48
    styleType
    -0.47
     opar
    -0.47
     boute
    -0.44
    hexyl
    -0.44
    joit
    -0.43
    DataBinding
    -0.43
     Demet
    -0.42
    POSITIVE LOGITS
     himself
    1.45
     Himself
    1.27
     themselves
    1.25
    himself
    1.22
     itself
    1.14
    themselves
    1.09
     yourselves
    1.04
    itself
    0.98
     ourselves
    0.95
    selves
    0.94
    Activations Density 1.506%

    No Known Activations