© 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. 4526
    Prev
    Next
    INDEX
    Explanations

    locations, phone numbers, email addresses, and anything in the possessive form

    oai_token-act-pair · gemini-2.0-flash

    programming code

    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
    Билгалдахарш
    -0.59
    onActivityResult
    -0.57
     <<<<<<<<<<<<<<
    -0.54
     considérons
    -0.52
    enumii
    -0.48
    matchCondition
    -0.48
    AddTagHelper
    -0.48
    UnifiedTopology
    -0.47
     مرئيه
    -0.47
     heartbeat
    -0.46
    POSITIVE LOGITS
    complexType
    0.63
    ::::::::
    0.57
    ">—
    0.56
    uyện
    0.54
    olera
    0.52
     Gainesville
    0.52
    ộn
    0.50
    +#+
    0.49
     Jol
    0.49
    CTIONS
    0.49
    Activations Density 0.686%

    No Known Activations