© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16069
    Prev
    Next
    INDEX
    Explanations

    computer brands and operating systems

    oai_token-act-pair · gemini-2.0-flash

    computers and software

    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
     propOrder
    -0.87
     الدولى
    -0.84
    StructEnd
    -0.84
     المعيارى
    -0.71
    +#+#
    -0.70
     utafitiHapana
    -0.70
     estekak
    -0.68
     Signalez
    -0.68
    LookAnd
    -0.67
    ViewImports
    -0.66
    POSITIVE LOGITS
     vanguardia
    0.42
    vism
    0.42
    LEncoder
    0.41
    Lz
    0.41
    tował
    0.41
    덱
    0.41
    Simple
    0.40
    rdom
    0.40
    ibos
    0.40
    Embeddable
    0.39
    Activations Density 0.744%

    No Known Activations