© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11784
    Prev
    Next
    INDEX
    Explanations

    indicators of progression or achievement

    oai_token-act-pair · gemini-2.0-flash

    Abstract goals

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     nhiên
    -0.52
     zvuky
    -0.49
    delin
    -0.48
    تاح
    -0.48
     enkelt
    -0.47
    accompag
    -0.46
    tide
    -0.46
    UnknownFieldSet
    -0.45
     Griechen
    -0.45
    ">//
    -0.45
    POSITIVE LOGITS
     maturity
    0.80
     victory
    0.69
     freedom
    0.69
     immortality
    0.68
     ***!
    0.68
     retirement
    0.68
    victory
    0.67
     martyrdom
    0.67
     adulthood
    0.66
    maturity
    0.65
    Activations Density 2.326%

    No Known Activations