© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13229
    Prev
    Next
    INDEX
    Explanations

    first and second person pronouns and related auxiliary verbs, as well as intensifiers

    oai_token-act-pair · gemini-2.0-flash

    detecting uncertainty

    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
     actual
    -2.56
    actual
    -2.52
     Actual
    -2.44
    Actual
    -2.42
     ACTUAL
    -2.28
     truly
    -2.20
    ACTUAL
    -2.19
     actually
    -2.09
     true
    -2.08
    truly
    -2.05
    POSITIVE LOGITS
    +#+#
    0.56
     utafitiHapana
    0.53
    complexContent
    0.52
     pinulongan
    0.49
    queryInterface
    0.48
    yntaxException
    0.48
    GOTREF
    0.47
    homonymie
    0.47
    ):}
    0.46
     iprot
    0.45
    Activations Density 4.799%

    No Known Activations