© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15260
    Prev
    Next
    INDEX
    Explanations

    words used to write or allude to discourse such as challenge, read, say, see, write, etc

    oai_token-act-pair · gemini-2.0-flash

    Groups and categories

    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
     juſ
    -0.77
     ſche
    -0.76
     uſed
    -0.69
    ſelf
    -0.65
     houſe
    -0.64
     ſtand
    -0.64
     ſen
    -0.63
     quæ
    -0.63
     ſtre
    -0.63
     ſou
    -0.63
    POSITIVE LOGITS
     Anti
    0.84
     Male
    0.78
     Human
    0.77
     Police
    0.76
     Non
    0.76
    şiv
    0.75
     Auto
    0.71
     Alcohol
    0.70
     Retail
    0.70
     Female
    0.70
    Activations Density 4.594%

    No Known Activations