© 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. 6525
    Prev
    Next
    INDEX
    Explanations

    mentions of working with cloth and tape.

    oai_token-act-pair · gemini-2.0-flash

    "roll"

    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
    ftagPool
    -0.52
     <>",
    -0.45
     Velcro
    -0.44
     zamknię
    -0.44
     tamaños
    -0.43
    textTheme
    -0.43
     vlož
    -0.42
    inflate
    -0.42
     ablation
    -0.42
     advies
    -0.42
    POSITIVE LOGITS
     rolls
    0.85
    
    0.82
     roll
    0.82
     Roll
    0.69
     ROLL
    0.66
    Obrázky
    0.64
    rolls
    0.62
     Rolls
    0.61
    roll
    0.60
    Roll
    0.60
    Activations Density 1.253%

    No Known Activations