© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1238
    Prev
    Next
    INDEX
    Explanations

    html table tags

    oai_token-act-pair · gemini-2.0-flash

    HTML table tags

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    <bos>
    -1.02
     itſelf
    -0.84
     raiſ
    -0.80
     Efq
    -0.77
     esternos
    -0.75
     reaſon
    -0.75
     pleaſure
    -0.74
     themſelves
    -0.72
     ſtate
    -0.72
     ་་
    -0.70
    POSITIVE LOGITS
     “
    0.56
    omar
    0.52
     Scroll
    0.50
    ίνει
    0.50
    NameValuePair
    0.50
    æa
    0.49
     ut
    0.48
    律
    0.48
    SOUNDBITE
    0.48
     uns
    0.48
    Activations Density 0.998%

    No Known Activations