© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7219
    Prev
    Next
    INDEX
    Explanations

    angle brackets enclosing the letters h, p, asp, te, ler, ik

    oai_token-act-pair · gemini-2.0-flash

    technical programming terms or code variables

    np_token-act-pair-logits · gpt-4o-mini

    GUI 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_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    SourceChecksum
    -0.63
    SharedCtor
    -0.49
    }*/
    -0.46
     initComponents
    -0.46
     facing
    -0.44
    ero
    -0.44
     pits
    -0.43
    facing
    -0.43
    Xna
    -0.42
    ParallelGroup
    -0.41
    POSITIVE LOGITS
    orianCalendar
    0.71
    BagLayout
    0.67
    astéroïdes
    0.64
    Datuak
    0.61
    hassee
    0.60
    onedDateTime
    0.60
     Lijst
    0.60
    ſelves
    0.57
     ſtate
    0.56
    )_/¯
    0.56
    Activations Density 1.210%

    No Known Activations