© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13824
    Prev
    Next
    INDEX
    Explanations

    TV station call letters and anything related to broadcast networks

    oai_token-act-pair · gemini-2.0-flash

    TV/Radio stations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    OrBuilder
    -0.62
     memen
    -0.48
    portlet
    -0.47
    inheritDoc
    -0.46
     g
    -0.46
     Usually
    -0.45
    keri
    -0.44
    翁
    -0.44
     esternos
    -0.44
    hasMoreElements
    -0.43
    POSITIVE LOGITS
    GEBURTSDATUM
    0.91
     للاسماء
    0.84
     InputDecoration
    0.82
    Distribuzione
    0.76
    OGND
    0.73
    SequentialGroup
    0.72
     ſche
    0.71
    LookAnd
    0.68
     ErrIntOverflow
    0.68
     OFDb
    0.68
    Activations Density 2.403%

    No Known Activations