© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10895
    Prev
    Next
    INDEX
    Explanations

    words that have "amp" in them, sometimes regardless of meaning, but sometimes related to amplification

    oai_token-act-pair · gemini-2.0-flash

    gene amplification and PCR

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Amp
    -2.59
     amp
    -2.55
    Amp
    -2.38
    amp
    -2.31
     amplifier
    -1.89
     amplification
    -1.87
     AMP
    -1.82
     amplify
    -1.79
    AMP
    -1.79
     amps
    -1.78
    POSITIVE LOGITS
     surla
    0.59
    sidemargin
    0.53
    InvalidProtocol
    0.52
    windowFixed
    0.52
     Schulte
    0.50
    verifyException
    0.49
     createSlice
    0.48
    hoga
    0.47
    ValueGenerated
    0.46
     Elie
    0.45
    Activations Density 1.896%

    No Known Activations