© 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. 3731
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to movement and exchange of material, possibly related to transactions or transferals.

    oai_token-act-pair · gemini-2.0-flash

    Delivering/Handing something

    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
    errHandler
    -0.91
     betweenstory
    -0.79
     صوتيه
    -0.71
     Roskov
    -0.66
    expandindo
    -0.63
    المناصب
    -0.62
     الحره
    -0.61
     فريبيس
    -0.61
    FunctionFlags
    -0.61
    CloseOperation
    -0.60
    POSITIVE LOGITS
     Ter
    0.50
    ándo
    0.49
     ter
    0.47
    XmlAccessorType
    0.45
    닷
    0.45
     peringkat
    0.44
     scale
    0.44
     ATTEND
    0.44
     attendance
    0.44
     Bauer
    0.42
    Activations Density 3.384%

    No Known Activations