© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6073
    Prev
    Next
    INDEX
    Explanations

    instances of direct address or instruction, especially in conversational contexts, potentially related to technical assistance.

    oai_token-act-pair · gemini-2.0-flash

    Internet chat/forum context

    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
     Theſe
    -0.84
     Anſ
    -0.81
     Monfieur
    -0.80
     ſeveral
    -0.78
     Reſ
    -0.78
     itſelf
    -0.77
    UnknownFieldSet
    -0.77
     whoſe
    -0.76
     myſelf
    -0.75
     Efq
    -0.74
    POSITIVE LOGITS
     referrerpolicy
    0.45
    串
    0.39
     s
    0.38
    ._
    0.38
     inc
    0.38
     [
    0.38
     nak
    0.38
    for
    0.37
    ART
    0.37
     «
    0.37
    Activations Density 0.923%

    No Known Activations