© 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. 14963
    Prev
    Next
    INDEX
    Explanations

    the text related to sports, and more specifically American football and basketball

    oai_token-act-pair · gemini-2.0-flash

    Sports

    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
    èdia
    -0.64
     незавершена
    -0.62
    findpost
    -0.60
     كومونز
    -0.58
     "..\..\
    -0.58
    ImageContext
    -0.54
    UnusedPrivate
    -0.54
    fjspx
    -0.52
    WireFormatLite
    -0.52
    MessageOf
    -0.51
    POSITIVE LOGITS
    oplayer
    0.56
    +#+#
    0.49
    plakat
    0.48
     pasted
    0.46
     mercies
    0.46
     springfox
    0.46
     ब्रेकडाउन
    0.45
    __((
    0.44
    mapsto
    0.44
     surfboard
    0.43
    Activations Density 3.552%

    No Known Activations