© 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. 15420
    Prev
    Next
    INDEX
    Explanations

    words related to legal and medical settings with possible connections to employees and authorized personnel

    oai_token-act-pair · gemini-2.0-flash

    present

    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
    styleType
    -0.83
    MigrationBuilder
    -0.72
    BeginContext
    -0.68
     Италијани
    -0.67
    UnusedPrivate
    -0.65
     linkovi
    -0.65
     uLocal
    -0.64
     betweenstory
    -0.63
    évaluateur
    -0.62
    yntaxException
    -0.61
    POSITIVE LOGITS
     present
    3.31
    present
    2.84
     Present
    2.73
    Present
    2.73
     PRESENT
    2.52
     présent
    2.36
     presente
    2.30
     prefent
    2.17
     présente
    2.16
     presentes
    2.08
    Activations Density 9.705%

    No Known Activations