© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12368
    Prev
    Next
    INDEX
    Explanations

    phrases indicating agreement, compromise, or getting along well with others

    oai_token-act-pair · gemini-2.0-flash

    along

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    Methode
    -0.50
    AppMethodBeat
    -0.48
    otide
    -0.47
    unto
    -0.47
     Alamofire
    -0.47
    marginVertical
    -0.47
    țin
    -0.46
     Moran
    -0.46
    Straße
    -0.46
     Nacionales
    -0.46
    POSITIVE LOGITS
     incompatible
    0.71
    compati
    0.70
     harmonious
    0.66
     concili
    0.66
     amic
    0.66
     friendliness
    0.64
    COMPAT
    0.63
     anlaş
    0.62
    UnknownFieldSet
    0.62
     reconciliation
    0.62
    Activations Density 0.954%

    No Known Activations