© 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. 14105
    Prev
    Next
    INDEX
    Explanations

    terms related to programming issues and troubleshooting

    oai_token-act-pair · gemini-2.0-flash

    Estou

    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
     énergétique
    -0.77
     المعيارى
    -0.68
     resourceCulture
    -0.65
     ProtoMessage
    -0.64
    ыгана
    -0.63
     ComVisible
    -0.57
     تانيه
    -0.57
    %)$
    -0.56
    DataSnapshot
    -0.56
    fris
    -0.56
    POSITIVE LOGITS
     officielles
    0.43
     ktoré
    0.43
    randomUUID
    0.42
    swire
    0.40
    drawSprites
    0.40
     LIBR
    0.39
     legal
    0.38
    onAttach
    0.38
    isateur
    0.38
     constitutional
    0.38
    Activations Density 0.209%

    No Known Activations