© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3262
    Prev
    Next
    INDEX
    Explanations

    technical or scientific terms related to sports, biology/chemistry.

    oai_token-act-pair · gemini-2.0-flash

    Technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     mergeFrom
    -0.69
    :✨
    -0.65
    TagHelper
    -0.63
    RUnlock
    -0.61
    dellín
    -0.60
     DBNull
    -0.59
    
    -0.59
    AndEndTag
    -0.59
    AsUp
    -0.56
     Савезне
    -0.56
    POSITIVE LOGITS
    तान
    0.54
     supérieures
    0.50
     mécanisme
    0.45
     effettuare
    0.45
     "/";
    0.45
    nocześnie
    0.45
     quelconque
    0.45
     noastră
    0.44
     zodia
    0.44
     générales
    0.43
    Activations Density 2.478%

    No Known Activations