© 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. 287
    Prev
    Next
    INDEX
    Explanations

    language related to legal proceedings and court decisions.

    oai_token-act-pair · gemini-2.0-flash

    Legal issues and cases

    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
    featureID
    -0.61
    Šaltiniai
    -0.61
    TagMode
    -0.59
     defStyleAttr
    -0.59
    DoubleQuotes
    -0.59
     numberOfRows
    -0.59
    rizona
    -0.57
    +#+
    -0.56
    thâu
    -0.56
    ThroughAttribute
    -0.56
    POSITIVE LOGITS
     stolen
    0.51
     estekak
    0.50
    AxisAlignment
    0.46
    stolen
    0.46
    Autoritní
    0.46
    gone
    0.45
     Stolen
    0.44
    ngdoc
    0.43
     "..\..\
    0.43
     lost
    0.42
    Activations Density 8.911%

    No Known Activations