© 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. 6043
    Prev
    Next
    INDEX
    Explanations

    html style tags related to fonts

    oai_token-act-pair · gemini-2.0-flash

    -

    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
    ficulty
    -0.87
    }{*}{}
    -0.78
    nicity
    -0.77
    ientôt
    -0.76
    ecake
    -0.76
    icrous
    -0.75
    cillor
    -0.74
    ecute
    -0.73
    igenous
    -0.73
    ']=='
    -0.72
    POSITIVE LOGITS
     OnTriggerEnter
    0.44
     maniere
    0.43
    ſelf
    0.42
    ContentAsync
    0.42
    new
    0.42
    c
    0.40
    re
    0.40
    one
    0.39
    from
    0.39
    ſelves
    0.39
    Activations Density 1.604%

    No Known Activations