© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14042
    Prev
    Next
    INDEX
    Explanations

    personal experiences and opinions, especially about reading, listening, or viewing of creative material

    oai_token-act-pair · gemini-2.0-flash

    reading and listening

    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
    endpush
    -0.62
     doInBackground
    -0.57
    migrationBuilder
    -0.49
    InBackground
    -0.48
     gyer
    -0.46
    hlas
    -0.45
     HasFactory
    -0.45
     Nacionales
    -0.44
    чению
    -0.43
    fél
    -0.43
    POSITIVE LOGITS
    PyExc
    0.64
    IUrlHelper
    0.63
     виправивши
    0.62
     تضيفلها
    0.62
    Personensuche
    0.61
    adaptiveStyles
    0.60
     mostrarán
    0.60
    verwijspagina
    0.60
    <?
    0.58
    kesha
    0.57
    Activations Density 27.399%

    No Known Activations