© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11876
    Prev
    Next
    INDEX
    Explanations

    various verbs related to tasks, work, or actions

    oai_token-act-pair · gemini-2.0-flash

    work

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    findpost
    -0.78
     Chwiliwch
    -0.72
    \{\\
    -0.70
    ⓧ
    -0.65
     صوتيه
    -0.64
    ScopeManager
    -0.63
     propOrder
    -0.63
    Билгалдахарш
    -0.61
    ьажоргаш
    -0.60
     nahilalakip
    -0.60
    POSITIVE LOGITS
    Iden
    0.51
    ARIES
    0.50
    axx
    0.50
     instantly
    0.45
     stab
    0.45
     Herren
    0.44
     analytically
    0.44
     dynamically
    0.44
     fru
    0.43
     digitally
    0.43
    Activations Density 5.298%

    No Known Activations