© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5283
    Prev
    Next
    INDEX
    Explanations

    sentences that attribute importance or the act of playing a role

    oai_token-act-pair · 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
     role
    -2.83
     Role
    -2.73
     roles
    -2.70
    Role
    -2.64
    role
    -2.59
     Roles
    -2.56
     ROLE
    -2.48
     rôle
    -2.36
    roles
    -2.28
    ROLE
    -2.28
    POSITIVE LOGITS
    存于互联网档案馆
    0.51
    
    0.48
    Билгалдахарш
    0.45
     indietro
    0.43
     ro
    0.42
    StoreMessageInfo
    0.41
    лтемелер
    0.41
    ोड़
    0.40
    enderror
    0.39
     متعلقه
    0.38
    Activations Density 0.966%

    No Known Activations