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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5334
    Prev
    Next
    INDEX
    Explanations

    mentions of electricity, particularly related to motors, cars and machines

    oai_token-act-pair · gemini-2.0-flash

    electric

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     giras
    -0.53
    šanās
    -0.50
     Dressing
    -0.49
    principalTable
    -0.48
    Dressing
    -0.46
    يين
    -0.46
    égi
    -0.45
     ['./
    -0.45
    gone
    -0.44
    chige
    -0.44
    POSITIVE LOGITS
    Autoritní
    0.65
    </thead>
    0.65
    Παραπομπές
    0.64
    ⓧ
    0.64
    RegressionTest
    0.64
    DrawerToggle
    0.63
    MLLoader
    0.62
     disambiguazione
    0.62
    ReusableCell
    0.61
    ThemeOverlay
    0.61
    Activations Density 2.568%

    No Known Activations