© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11680
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to mobile app development and business

    oai_token-act-pair · gemini-2.0-flash

    Miscellaneous general text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    StructEnd
    -1.08
     betweenstory
    -1.04
    +#+#
    -1.02
    yntaxException
    -1.01
     ProtoMessage
    -0.95
    parsedMessage
    -0.93
     <=",
    -0.92
    setVerticalGroup
    -0.91
     تضيفلها
    -0.86
    Referanser
    -0.82
    POSITIVE LOGITS
    thaler
    0.50
    total
    0.47
    saraba
    0.44
     européens
    0.41
     nélkül
    0.41
    ate
    0.41
    idon
    0.41
     total
    0.40
     provincias
    0.40
    ftest
    0.39
    Activations Density 0.420%

    No Known Activations