© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10585
    Prev
    Next
    INDEX
    Explanations

    references to lengths of time

    oai_token-act-pair · gemini-2.0-flash

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    ur
    -0.63
     o
    -0.53
    ↵↵
    -0.53
     U
    -0.52
    and
    -0.51
    -
    -0.51
     ur
    -0.49
     "
    -0.49
     Erişim
    -0.49
     B
    -0.49
    POSITIVE LOGITS
     myſelf
    1.29
     Efq
    1.29
     Monfieur
    1.23
     Theſe
    1.18
     Jefus
    1.16
     themſelves
    1.15
     Houſe
    1.13
     purpoſe
    1.12
     himſelf
    1.11
     Eſ
    1.11
    Activations Density 2.179%

    No Known Activations