© 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. 3972
    Prev
    Next
    INDEX
    Explanations

    language related to criminal defense

    oai_token-act-pair · gemini-2.0-flash

    Legal defense/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
     defense
    -2.72
     defence
    -2.64
     Defense
    -2.44
    Defense
    -2.38
     defensive
    -2.36
     Defence
    -2.30
    Defence
    -2.28
    Def
    -2.25
    def
    -2.23
     DEFENSE
    -2.23
    POSITIVE LOGITS
    kháu
    0.58
    skraft
    0.48
     sond
    0.45
     урна
    0.45
    toplankton
    0.43
     GeoNames
    0.42
    ImageContext
    0.41
     '../../../../
    0.41
    ører
    0.41
    bliž
    0.41
    Activations Density 3.473%

    No Known Activations