© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6540
    Prev
    Next
    INDEX
    Explanations

    fundraising campaign information

    oai_token-act-pair · gemini-2.0-flash

    fundraising/donations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ấu
    -0.51
    rungsseite
    -0.49
    bar
    -0.45
    thing
    -0.44
     bar
    -0.43
    MISS
    -0.43
     barre
    -0.43
    好
    -0.43
    BAR
    -0.43
    バー
    -0.43
    POSITIVE LOGITS
    GraphicsUnit
    0.65
     transfieras
    0.65
    AndEndTag
    0.64
    EDEFAULT
    0.64
    archiviato
    0.63
    Nazionale
    0.63
     يتيمه
    0.60
    CloseOperation
    0.60
    kadang
    0.60
     الرياضيه
    0.60
    Activations Density 9.919%

    No Known Activations