© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11316
    Prev
    Next
    INDEX
    Explanations

    the word "up" and the word "off", sometimes combined with "over"

    oai_token-act-pair · gemini-2.0-flash

    prepositions up/off

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    IntoConstraints
    -0.99
     @"/
    -0.83
    djangoproject
    -0.81
     MainAxisSize
    -0.77
     otomatig
    -0.75
    AndEndTag
    -0.74
    interopRequire
    -0.73
    Xna
    -0.73
    webElementGuid
    -0.72
     estimés
    -0.72
    POSITIVE LOGITS
     up
    0.59
    up
    0.49
     Eichen
    0.47
     into
    0.47
    தே
    0.44
    ups
    0.43
     upon
    0.42
     around
    0.42
    tehenden
    0.41
     about
    0.41
    Activations Density 0.149%

    No Known Activations