© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11375
    Prev
    Next
    INDEX
    Explanations

    code related to accessing data items

    oai_token-act-pair · gemini-2.0-flash

    Code and markup

    np_max-act-logits · gemini-2.0-flash

    punctuation

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     It
    -0.65
     «
    -0.61
     The
    -0.61
     “
    -0.58
     We
    -0.56
     "
    -0.54
     I
    -0.53
     That
    -0.52
     But
    -0.52
    ARIOS
    -0.51
    POSITIVE LOGITS
     photolibrary
    0.99
     Efq
    0.98
     Diſ
    0.95
     Houſe
    0.93
     himſelf
    0.93
     Normdatei
    0.90
     myſelf
    0.90
     sportback
    0.89
     itſelf
    0.88
     Anſ
    0.87
    Activations Density 5.519%

    No Known Activations