© 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. 2361
    Prev
    Next
    INDEX
    Explanations

    words indicating the position of something

    oai_token-act-pair · gemini-2.0-flash

    location/section of things

    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
    #+#
    -0.75
     front
    -0.73
     inside
    -0.73
    SequentialGroup
    -0.70
     upper
    -0.70
     middle
    -0.69
     interior
    -0.68
     &___
    -0.68
     centre
    -0.66
    beginning
    -0.66
    POSITIVE LOGITS
     فريبيس
    0.68
    ReusableCell
    0.50
     area
    0.45
    部に
    0.44
     widerrufen
    0.43
    strut
    0.43
    grà
    0.42
    ಭ
    0.42
     part
    0.42
    icular
    0.41
    Activations Density 2.082%

    No Known Activations