© 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. 12939
    Prev
    Next
    INDEX
    Explanations

    clauses starting with "it" or "that".

    oai_token-act-pair · gemini-2.0-flash

    variations of "mean"

    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
    -0.59
    HAEL
    -0.52
    fromnode
    -0.48
    routeProvider
    -0.47
     ogóle
    -0.44
    ţion
    -0.44
    一样
    -0.44
    dalena
    -0.43
    chos
    -0.43
    FECTION
    -0.43
    POSITIVE LOGITS
     means
    2.44
     meant
    2.30
    means
    2.19
     Means
    2.17
     MEANS
    2.14
     mean
    2.13
    Means
    2.09
    meant
    1.92
     Mean
    1.77
     MEAN
    1.74
    Activations Density 2.157%

    No Known Activations