© 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. 14873
    Prev
    Next
    INDEX
    Explanations

    language related to criminal charges and legal proceedings

    oai_token-act-pair · gemini-2.0-flash

    criminal charges

    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
     дописавши
    -0.79
     المعيارى
    -0.69
    parsedMessage
    -0.63
    makeConstraints
    -0.62
    buttonBar
    -0.62
    __':
    -0.60
    __":
    -0.60
    ChildIndex
    -0.59
    ."));
    -0.59
    脚注の使い方
    -0.59
    POSITIVE LOGITS
     تانيه
    0.66
    krivning
    0.54
    bės
    0.52
     commandé
    0.51
     fidu
    0.51
     Normdatei
    0.51
     carmen
    0.49
     खरीदा
    0.48
     satunya
    0.48
    یره
    0.48
    Activations Density 2.908%

    No Known Activations