© 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. 11354
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and parenthesis

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
     Efq
    -0.77
     Houſe
    -0.77
     houſe
    -0.75
     pleaſure
    -0.74
     ――――
    -0.71
     ―――
    -0.69
     Shakspeare
    -0.69
     leaſt
    -0.68
     fevere
    -0.68
     Monfieur
    -0.68
    POSITIVE LOGITS
     And
    0.50
     AssemblyCulture
    0.48
     Man
    0.48
     To
    0.48
     He
    0.47
    zerne
    0.46
    LookAnd
    0.46
     fortsatt
    0.46
    Kanpo
    0.45
     Créez
    0.45
    Activations Density 4.716%

    No Known Activations