© 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. 12640
    Prev
    Next
    INDEX
    Explanations

    references to movie production.

    oai_token-act-pair · gemini-2.0-flash

    words related to film production

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

    media production

    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
     itſelf
    -0.94
     Efq
    -0.90
     estekak
    -0.83
    ſelves
    -0.82
     autorytatywna
    -0.80
     myſelf
    -0.80
     Jefus
    -0.79
     فريبيس
    -0.79
     purpoſe
    -0.75
     whoſe
    -0.74
    POSITIVE LOGITS
    不出
    0.48
     rela
    0.47
     box
    0.46
     bank
    0.44
     теле
    0.43
    青
    0.42
     υ
    0.42
     general
    0.42
    orin
    0.41
    ox
    0.41
    Activations Density 2.469%

    No Known Activations