© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14205
    Prev
    Next
    INDEX
    Explanations

    mentions of motor vehicles

    oai_token-act-pair · gemini-2.0-flash

    motor

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    хьтан
    -0.91
     المعيارى
    -0.91
     للاسماء
    -0.85
    matchCondition
    -0.84
    LookAnd
    -0.84
    httphttps
    -0.82
    ⓧ
    -0.81
     '\\;'
    -0.81
    IntoConstraints
    -0.80
     AssemblyCompany
    -0.79
    POSITIVE LOGITS
     inn
    0.37
    `),
    0.36
    }();
    0.36
     kend
    0.36
     cross
    0.34
     himo
    0.34
    cross
    0.34
    omar
    0.33
    bun
    0.32
    ol
    0.32
    Activations Density 0.751%

    No Known Activations