© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7768
    Prev
    Next
    INDEX
    Explanations

    words relating to research and also what appears to be hebrew characters and some underscores followed by numbers

    oai_token-act-pair · gemini-2.0-flash

    technical and code mixed text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Majefty
    -1.38
     Efq
    -1.34
     Jefus
    -1.30
     Anſ
    -1.27
     Diſ
    -1.23
     leaſt
    -1.22
     Eſ
    -1.20
     ſeveral
    -1.20
     Reſ
    -1.19
     myſelf
    -1.17
    POSITIVE LOGITS
     suger
    0.22
    <eos>
    0.20
    ↵↵
    0.19
    חר
    0.19
    ...
    0.18
     komplex
    0.18
    \
    0.17
     konflikt
    0.17
    (
    0.16
    -
    0.16
    Activations Density 0.053%

    No Known Activations