© 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-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5513
    Prev
    Next
    INDEX
    Explanations

    what appears to be proper nouns, often names (potentially including abbreviations or nicknames).

    oai_token-act-pair · gemini-2.0-flash

    F

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     fourrure
    -0.46
    assemblée
    -0.44
    g
    -0.41
    échelle
    -0.39
    m
    -0.39
    entraînement
    -0.39
    ge
    -0.39
     poupée
    -0.38
    pu
    -0.38
    mal
    -0.38
    POSITIVE LOGITS
     Roskov
    0.49
     gynhyrchwyd
    0.46
     '\\;'
    0.44
    ыгана
    0.44
     autorytatywna
    0.44
     lenker
    0.44
    :✨
    0.43
     Италијани
    0.43
     Wikimedijinoj
    0.42
    UnusedPrivate
    0.42
    Activations Density 5.517%

    No Known Activations