© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6459
    Prev
    Next
    INDEX
    Explanations

    uses the align environment for equations in LaTeX

    oai_token-act-pair · gemini-2.0-flash

    the term "aligned"

    np_token-act-pair-logits · gpt-4o-mini

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     stabilité
    -0.56
     "'");
    -0.55
    >());
    -0.52
    )))),
    -0.51
    EndInit
    -0.50
     ""))
    -0.49
     ?>>
    -0.48
     strade
    -0.48
     spécial
    -0.46
    <eos>
    -0.46
    POSITIVE LOGITS
    tvguidetime
    0.81
    brainly
    0.74
    ArgsConstructor
    0.68
    Enllaces
    0.67
    ſelf
    0.67
     مرئيه
    0.66
    ^(@)
    0.66
    felf
    0.65
    ItemLayout
    0.63
     itſelf
    0.61
    Activations Density 0.045%

    No Known Activations