© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13978
    Prev
    Next
    INDEX
    Explanations

    code and markup

    oai_token-act-pair · gemini-2.0-flash

    tokens starting with an underscore

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

    Code or programming context

    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
     
    -0.75
    <eos>
    -0.63
     "
    -0.58
     it
    -0.56
     \
    -0.54
     I
    -0.53
     P
    -0.49
     *
    -0.49
     “
    -0.49
     F
    -0.49
    POSITIVE LOGITS
     itſelf
    1.00
     MainAxisSize
    0.87
     crdi
    0.85
     ſtate
    0.84
     raiſ
    0.82
     myſelf
    0.81
     poffible
    0.81
    ^(@)
    0.80
     reaſon
    0.80
     Reſ
    0.79
    Activations Density 0.427%

    No Known Activations