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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10554
    Prev
    Next
    INDEX
    Explanations

    names of car models

    oai_token-act-pair · gemini-2.0-flash

    Š

    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
    自
    -0.47
     «
    -0.44
    templateUrl
    -0.43
    __).
    -0.43
     Levin
    -0.43
    QString
    -0.42
    ]])
    -0.41
     the
    -0.40
     Gilman
    -0.40
     »
    -0.40
    POSITIVE LOGITS
    featureID
    1.02
     تانيه
    0.88
     autorytatywna
    0.85
    expandindo
    0.81
     Efq
    0.81
     disambiguazione
    0.80
     AssemblyCulture
    0.79
    MessageTagHelper
    0.77
     referenties
    0.76
     preſent
    0.74
    Activations Density 0.293%

    No Known Activations