© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3150
    Prev
    Next
    INDEX
    Explanations

    advertising copy for hotels, restaurants or travel

    oai_token-act-pair · gemini-2.0-flash

    experience

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     незавершена
    -0.82
    TagMode
    -0.72
    Vidite
    -0.71
     otomatig
    -0.65
    orianCalendar
    -0.64
     lenker
    -0.63
     forState
    -0.61
    IsContent
    -0.60
    ngths
    -0.60
     AssemblyVersion
    -0.59
    POSITIVE LOGITS
    Distinct
    0.45
    πον
    0.45
     ComVisible
    0.44
     this
    0.44
     interesting
    0.43
     т
    0.41
    enumi
    0.40
    interesting
    0.39
     the
    0.38
     an
    0.38
    Activations Density 4.211%

    No Known Activations