© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9075
    Prev
    Next
    INDEX
    Explanations

    the word "place", and sometimes something in the vicinity.

    oai_token-act-pair · gemini-2.0-flash

    place

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     part
    -0.54
     media
    -0.47
    motion
    -0.45
     sub
    -0.44
    CORBA
    -0.44
     instead
    -0.44
     fire
    -0.43
     Protección
    -0.43
    ”,
    -0.43
     состоя
    -0.43
    POSITIVE LOGITS
    MigrationBuilder
    0.82
    Hentet
    0.73
    Архівовано
    0.67
    tagHelperRunner
    0.65
    期刊论文
    0.64
    migrationBuilder
    0.64
    AsUp
    0.63
     takers
    0.63
    日閲覧
    0.63
    érêt
    0.63
    Activations Density 1.567%

    No Known Activations