© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 2055
    Prev
    Next
    INDEX
    Explanations

    code snippets

    oai_token-act-pair · gemini-2.0-flash

    Code syntax

    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
    .
    -0.50
    ,
    -0.39
    (
    -0.37
    ↵↵
    -0.37
    .:
    -0.36
    ↵
    -0.33
    .”
    -0.32
    ↵↵↵
    -0.31
    :
    -0.30
    .,
    -0.29
    POSITIVE LOGITS
     itſelf
    0.88
     iſt
    0.87
     purpoſe
    0.84
     Houſe
    0.84
    ſelf
    0.83
    ſelves
    0.82
     myſelf
    0.82
     houſe
    0.81
    CHREIB
    0.81
     ſtate
    0.80
    Activations Density 8.556%

    No Known Activations