© 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. 5330
    Prev
    Next
    INDEX
    Explanations

    words and word fragments that have the letters "cat", "in" and "is" in them

    oai_token-act-pair · gemini-2.0-flash

    ion

    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
    TagMode
    -0.70
    enumi
    -0.66
     الحره
    -0.65
    ://$
    -0.59
     transférez
    -0.58
    MLLoader
    -0.56
    audiovisuel
    -0.56
    TAWA
    -0.55
    wade
    -0.55
     saper
    -0.55
    POSITIVE LOGITS
     ion
    0.75
     ION
    0.70
    Ion
    0.68
    ion
    0.65
    Ton
    0.64
     Ion
    0.64
     ions
    0.64
    jon
    0.63
    jons
    0.62
     Ton
    0.62
    Activations Density 1.078%

    No Known Activations