© 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. 10570
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially names of places and organizations, and the letters "le"

    oai_token-act-pair · gemini-2.0-flash

    European place names and names

    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
     m
    -0.65
     M
    -0.58
     D
    -0.57
     
    -0.57
     un
    -0.56
     Di
    -0.56
     F
    -0.56
     S
    -0.56
     x
    -0.56
     s
    -0.55
    POSITIVE LOGITS
    цездатний
    0.89
    Personensuche
    0.81
     Paglinawan
    0.81
    évaluateur
    0.80
    ValueStyle
    0.79
    IntoConstraints
    0.79
     itſelf
    0.77
     мәкал
    0.75
    SourceChecksum
    0.75
    ImageContext
    0.75
    Activations Density 0.490%

    No Known Activations