© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7446
    Prev
    Next
    INDEX
    Explanations

    words related to movies and film production

    oai_token-act-pair · gemini-2.0-flash

    diverse or foreign terms

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

    movies and shows

    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
    ModelSerializer
    -0.52
    UrlEncoded
    -0.49
    جل
    -0.44
    ticle
    -0.42
     o
    -0.40
     volte
    -0.40
     впер
    -0.40
     volume
    -0.40
    InSection
    -0.38
     theirs
    -0.38
    POSITIVE LOGITS
    rungsseite
    0.93
    Tikang
    0.79
    AddTagHelper
    0.77
    الحياه
    0.74
    principalTable
    0.73
     AssemblyTitle
    0.72
    Datuak
    0.71
    
    0.71
    DoubleQuotes
    0.71
    StreetMap
    0.69
    Activations Density 1.142%

    No Known Activations