© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1410
    Prev
    Next
    INDEX
    Explanations

    mentions of television

    oai_token-act-pair · gemini-2.0-flash

    TV

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     TV
    -2.30
    TV
    -2.06
     television
    -1.91
     tv
    -1.90
    tv
    -1.76
     Television
    -1.65
    Television
    -1.62
     Tv
    -1.57
    television
    -1.51
    Tv
    -1.49
    POSITIVE LOGITS
    principalColumn
    0.94
     protoimpl
    0.77
    WriteTagHelper
    0.76
    DebuggerNonUser
    0.75
    windowFixed
    0.69
    enumi
    0.66
     Exacts
    0.65
    Amicalement
    0.65
     betweenstory
    0.64
     AssemblyVersion
    0.64
    Activations Density 2.260%

    No Known Activations