© 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. 13029
    Prev
    Next
    INDEX
    Explanations

    language that criticizes the US Federal Reserve and its monetary policy and predicts the downfall of the US dollar.

    oai_token-act-pair · gemini-2.0-flash

    peg

    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
     صوتيه
    -0.58
     StatelessWidget
    -0.58
     financeira
    -0.53
    dims
    -0.52
     empleo
    -0.52
     gants
    -0.50
     financière
    -0.50
    ocity
    -0.50
    findpost
    -0.49
     sonno
    -0.49
    POSITIVE LOGITS
    peg
    0.76
     peg
    0.76
     backed
    0.76
     Peg
    0.74
     pegged
    0.71
     tying
    0.67
    tvguidetime
    0.66
     geko
    0.65
    PostBack
    0.64
    Peg
    0.63
    Activations Density 2.172%

    No Known Activations