© 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. 9276
    Prev
    Next
    INDEX
    Explanations

    words and short phrases in a police crime report

    oai_token-act-pair · gemini-2.0-flash

    crime scenes/apartments

    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
    WindowConstants
    -0.58
     Мексичка
    -0.57
     дописавши
    -0.48
     transfieras
    -0.48
    ApiModel
    -0.47
    İstinadlar
    -0.47
    setVerticalGroup
    -0.47
    depend
    -0.45
     affiliation
    -0.44
    ➟
    -0.44
    POSITIVE LOGITS
     يتيمه
    0.71
    colgroup
    0.60
    曖昧さ回避
    0.58
     AssemblyVersion
    0.54
     artificiales
    0.54
    *)((
    0.53
    GEBURTSDATUM
    0.52
    PhysRevLett
    0.51
     تضيفلها
    0.50
    tettu
    0.50
    Activations Density 6.356%

    No Known Activations