© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5658
    Prev
    Next
    INDEX
    Explanations

    the phrase "on top of" and other instances of "on" and "out" used as prepositions

    oai_token-act-pair · gemini-2.0-flash

    words related to 'top' or 'layer'

    np_token-act-pair-logits · gpt-4o-mini

    top

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     AssemblyCulture
    -1.17
     للمعارف
    -1.17
     <<<<<<<<<<<<<<
    -1.02
    LookAnd
    -0.96
     незавершена
    -0.95
    Personendaten
    -0.88
    +:+
    -0.87
    verwijspagina
    -0.85
     estekak
    -0.83
    AnchorStyles
    -0.82
    POSITIVE LOGITS
     top
    3.11
    top
    2.53
    Top
    2.11
     Top
    2.06
    TOP
    1.78
     TOP
    1.73
     tops
    1.73
     on
    1.60
    トップ
    1.57
    tops
    1.44
    Activations Density 1.062%

    No Known Activations