© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11064
    Prev
    Next
    INDEX
    Explanations

    the word "to" followed by a verb

    oai_token-act-pair · gemini-2.0-flash

    to

    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
     most
    -0.52
     olympiques
    -0.45
     rocher
    -0.44
     délic
    -0.43
    Most
    -0.43
    N
    -0.41
    اح
    -0.41
    most
    -0.40
     rayures
    -0.40
     vanlig
    -0.40
    POSITIVE LOGITS
     disambiguazione
    1.01
    Portale
    0.94
    bootstrapcdn
    0.84
     nakalista
    0.80
    aarrggbb
    0.80
    oredCriteria
    0.72
    OGND
    0.72
     يتيمه
    0.71
    DoubleQuotes
    0.71
    ########.
    0.70
    Activations Density 1.377%

    No Known Activations