© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6285
    Prev
    Next
    INDEX
    Explanations

    the word "a" preceded by some verb of searching and followed by a word indicating a path or resolution, such as "solution" or "way," or by words describing something new, like "new wife"

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the token "a"

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

    a

    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
     BorderRadius
    -0.59
     finds
    -0.55
    VersionUID
    -0.52
     Finds
    -0.51
     Find
    -0.48
    Хьажоргаш
    -0.48
     find
    -0.47
    Find
    -0.46
    FIND
    -0.46
     encontra
    -0.45
    POSITIVE LOGITS
     way
    0.82
    NameInMap
    0.77
    السكان
    0.71
    WebElementEntity
    0.68
    IsContent
    0.66
     estekak
    0.65
    way
    0.64
    出版年
    0.64
    ]--;
    0.63
     Normdatei
    0.61
    Activations Density 1.308%

    No Known Activations