© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4893
    Prev
    Next
    INDEX
    Explanations

    legal or formal language related to evidence, presentation, and argument

    oai_token-act-pair · gemini-2.0-flash

    present

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    __':
    -0.72
    __":
    -0.69
     InputDecoration
    -0.65
     defStyleAttr
    -0.54
     Wiktionnaire
    -0.50
    lloworld
    -0.49
     Majesté
    -0.48
    IsMutable
    -0.48
    DeleteBehavior
    -0.47
     Mentre
    -0.47
    POSITIVE LOGITS
     resourceCulture
    0.69
    Preferences
    0.68
    IFIER
    0.67
    nadequate
    0.66
    opla
    0.66
     AppCompat
    0.65
    uitable
    0.62
     Physiol
    0.61
    ERES
    0.61
    atize
    0.60
    Activations Density 1.664%

    No Known Activations