© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10592
    Prev
    Next
    INDEX
    Explanations

    film credits and award nominations

    oai_token-act-pair · gemini-2.0-flash

    film credits and cast details

    np_token-act-pair-logits · gpt-4o-mini

    movies/plays with actors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    getMenuInflater
    -0.65
    kosť
    -0.55
     BioLib
    -0.54
     jspb
    -0.54
    complexContent
    -0.53
    RSpec
    -0.53
     تعدى
    -0.53
     mapStateToProps
    -0.52
     Passing
    -0.52
    Tracce
    -0.52
    POSITIVE LOGITS
    帖最后由
    0.52
    ensaft
    0.51
    ienes
    0.46
    formable
    0.46
    {:
    0.44
    dflare
    0.43
    رى
    0.43
    ypal
    0.42
    genicity
    0.41
     character
    0.40
    Activations Density 1.973%

    No Known Activations