© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13963
    Prev
    Next
    INDEX
    Explanations

    math, coding, and certain words from common expressions such as "i.e."

    oai_token-act-pair · gemini-2.0-flash

    math variable i

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     itſelf
    -1.00
     myſelf
    -0.98
    :✨
    -0.97
     nakalista
    -0.93
     Efq
    -0.92
    ?».
    -0.91
    ).'
    -0.89
    ).]
    -0.88
    NUMX
    -0.88
     poffible
    -0.86
    POSITIVE LOGITS
    .
    2.39
     .
    0.64
    ．
    0.52
    ._
    0.48
    .(
    0.43
    .\
    0.38
    ..
    0.38
    c
    0.35
    _
    0.35
    *.
    0.35
    Activations Density 6.166%

    No Known Activations