© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2154
    Prev
    Next
    INDEX
    Explanations

    time stamps and software version numbers in log-like data

    oai_token-act-pair · gemini-2.0-flash

    say 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_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     наук
    -0.43
    ؤية
    -0.41
     перио
    -0.40
     N
    -0.39
    libft
    -0.39
    tedt
    -0.38
    不止
    -0.38
    [
    -0.38
     来自
    -0.38
     conci
    -0.38
    POSITIVE LOGITS
     itſelf
    0.88
     myſelf
    0.85
    ſelf
    0.83
     Efq
    0.76
    ſelves
    0.76
    PerformLayout
    0.75
     defire
    0.71
     himſelf
    0.71
     Monfieur
    0.69
     pleaſure
    0.67
    Activations Density 1.591%

    No Known Activations