© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7302
    Prev
    Next
    INDEX
    Explanations

    words used in the field of astrophysics, particularly those related to galaxy observation and gravitational lensing

    oai_token-act-pair · gemini-2.0-flash

    galaxies and CMB lensing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    地に
    -0.48
     anklicken
    -0.48
    IsContent
    -0.46
     bearbeitet
    -0.45
     citer
    -0.45
     contacter
    -0.44
    ánto
    -0.44
    impre
    -0.43
     impré
    -0.43
     bears
    -0.42
    POSITIVE LOGITS
     CreateTagHelper
    0.79
    SuppressLint
    0.69
     nahilalakip
    0.68
    migrationBuilder
    0.67
    ngdoc
    0.66
    ########.
    0.63
    gameserver
    0.62
    SuppressMessage
    0.61
     通販
    0.60
    posedge
    0.59
    Activations Density 2.855%

    No Known Activations