© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8739
    Prev
    Next
    INDEX
    Explanations

    prepositions and words or phrases that commonly follow them.

    oai_token-act-pair · gemini-2.0-flash

    technical terms or programming syntax

    np_token-act-pair-logits · gpt-4o-mini

    up

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     up
    -1.30
     out
    -0.98
    up
    -0.97
     Up
    -0.85
     down
    -0.79
     UP
    -0.77
     Numerade
    -0.76
     nahilalakip
    -0.75
    Up
    -0.75
    ")){
    -0.74
    POSITIVE LOGITS
     textStatus
    0.54
    뀐
    0.44
    뀔
    0.44
    PerformLayout
    0.42
    IntoConstraints
    0.42
     croit
    0.41
     Escolar
    0.41
    뀜
    0.41
    EditorBrowsable
    0.41
     صوتيه
    0.41
    Activations Density 12.388%

    No Known Activations