© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9304
    Prev
    Next
    INDEX
    Explanations

    words related to cars and their features

    oai_token-act-pair · gemini-2.0-flash

    engines and cars

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     []:
    -0.60
    )++;
    -0.56
    tagHelperRunner
    -0.54
    ViewImports
    -0.52
     numberWith
    -0.51
    archiviato
    -0.50
     '{@
    -0.50
    apos
    -0.49
     NSCoder
    -0.48
    heli
    -0.47
    POSITIVE LOGITS
    ContentAsync
    0.52
    phorbia
    0.51
    Slf
    0.50
     joints
    0.48
     nahilalakip
    0.47
    DllImport
    0.46
    ignées
    0.45
     Locus
    0.45
     otomatig
    0.45
     lenses
    0.44
    Activations Density 7.487%

    No Known Activations