© 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. 14710
    Prev
    Next
    INDEX
    Explanations

    the verb "be" in various tenses and forms, sometimes in conjunction with "made" or "money".

    oai_token-act-pair · gemini-2.0-flash

    say "made"

    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
     Make
    -2.44
    Make
    -2.42
     make
    -2.41
    make
    -2.36
     MAKE
    -2.23
     makes
    -2.14
    MAKE
    -2.14
     Makes
    -2.08
    makes
    -2.06
    Makes
    -2.02
    POSITIVE LOGITS
    ValueStyle
    0.77
    Portail
    0.67
    TagMode
    0.65
    İstinadlar
    0.58
     NSCoder
    0.58
    下载附件
    0.57
    okovic
    0.57
    Vidite
    0.54
    prepareStatement
    0.54
    HtmlAttribute
    0.54
    Activations Density 3.399%

    No Known Activations