© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15470
    Prev
    Next
    INDEX
    Explanations

    the prefix "prop"

    oai_token-act-pair · gemini-2.0-flash

    prop

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    .
    -1.20
    ↵↵
    -1.20
    ,
    -1.17
    -
    -1.15
    <eos>
    -1.10
    _
    -1.09
    ↵
    -1.02
    2
    -1.02
     and
    -0.98
     -
    -0.94
    POSITIVE LOGITS
     ―――――
    1.80
     myſelf
    1.75
    NUMX
    1.73
    ſelf
    1.67
    ^(@)
    1.64
     $_"
    1.64
     iſt
    1.63
     itſelf
    1.63
     Forumite
    1.60
    ſelves
    1.59
    Activations Density 2.217%

    No Known Activations