© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14182
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers and codes

    oai_token-act-pair · gemini-2.0-flash

    e

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     onCreateView
    -0.66
    InputBorder
    -0.65
     InputDecoration
    -0.65
    hloromethane
    -0.63
    AddTagHelper
    -0.59
    hydrates
    -0.58
     égard
    -0.57
    entiated
    -0.56
    onActivityResult
    -0.54
     برانيه
    -0.54
    POSITIVE LOGITS
    tvguidetime
    0.74
    帖最后由
    0.73
    GenerationType
    0.63
    évaluateur
    0.56
    transQ
    0.53
     PropTypes
    0.51
    Expert
    0.49
     zás
    0.49
    ConstraintMaker
    0.48
    WebServlet
    0.47
    Activations Density 10.685%

    No Known Activations