© 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. 1510
    Prev
    Next
    INDEX
    Explanations

    the beginning of for loops of all types in various programming languages

    oai_token-act-pair · gemini-2.0-flash

    Parenthesis

    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
     Voici
    -0.50
    /***/
    -0.48
     without
    -0.47
    ohne
    -0.47
     shalt
    -0.47
    without
    -0.46
     "..\..\
    -0.46
    ,
    -0.46
    .
    -0.46
    StoryboardSegue
    -0.46
    POSITIVE LOGITS
     BoxDecoration
    0.64
    UserScript
    0.61
    AutoField
    0.55
    pædia
    0.54
    JsonKey
    0.53
    prefixer
    0.53
    льти
    0.52
    reactstrap
    0.51
    acabana
    0.51
    enumi
    0.51
    Activations Density 3.355%

    No Known Activations