© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3686
    Prev
    Next
    INDEX
    Explanations

    references to a defined space or place

    oai_token-act-pair · gemini-2.0-flash

    area

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Bogen
    -0.59
     AssertionError
    -0.58
    Varint
    -0.57
     Monfieur
    -0.56
     purpoſe
    -0.53
     tabindex
    -0.52
     nahilalakip
    -0.52
     ainfi
    -0.52
    òng
    -0.51
     filial
    -0.51
    POSITIVE LOGITS
    aarrggbb
    0.60
    ExecuteReader
    0.59
     NSCoder
    0.57
     autorytatywna
    0.54
    UnsafeEnabled
    0.53
    VersionUID
    0.48
     of
    0.48
    .*")]
    0.47
     recevrez
    0.45
    __":
    0.45
    Activations Density 9.622%

    No Known Activations