© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11122
    Prev
    Next
    INDEX
    Explanations

    words that appear to be from a South Asian language

    oai_token-act-pair · gemini-2.0-flash

    restaurant reviews

    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
    principalTable
    -0.59
    MessageOf
    -0.50
    iotensin
    -0.49
    +#+#
    -0.49
    HasForeignKey
    -0.49
    potranspiration
    -0.48
     חיצוניים
    -0.48
    oughly
    -0.48
    postIndex
    -0.47
    MENAFN
    -0.47
    POSITIVE LOGITS
    TestingModule
    0.68
    nation
    0.51
    teln
    0.50
     ThemeData
    0.49
     justices
    0.47
    óricas
    0.47
    Nation
    0.47
    SEL
    0.47
    spot
    0.46
    DOCT
    0.46
    Activations Density 0.395%

    No Known Activations