© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8676
    Prev
    Next
    INDEX
    Explanations

    text relating to Irish sports figures

    oai_token-act-pair · gemini-2.0-flash

    Ireland sports and places

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    addPreferredGap
    -0.69
    Tikang
    -0.68
    ंदीखरीदारी
    -0.68
    ConstraintMaker
    -0.65
    ParallelGroup
    -0.62
    וויק
    -0.62
    BufferException
    -0.62
    saraba
    -0.62
    сылкі
    -0.59
    makeText
    -0.58
    POSITIVE LOGITS
    yntaxException
    0.53
     تانيه
    0.49
     المتحدة
    0.48
    encji
    0.47
    panels
    0.47
    )))));
    0.46
     mondeo
    0.45
     étrang
    0.44
     Refinery
    0.43
    ")));
    0.43
    Activations Density 0.752%

    No Known Activations