© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1463
    Prev
    Next
    INDEX
    Explanations

    words related to schools, cars, and airports

    oai_token-act-pair · gemini-2.0-flash

    transport and school

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     nakalista
    -0.71
    complexType
    -0.71
    TintMode
    -0.70
    
    -0.69
    ormick
    -0.68
    +#+#
    -0.67
     onPostExecute
    -0.66
    WriteAttribute
    -0.66
     makeStyles
    -0.66
     дописавши
    -0.65
    POSITIVE LOGITS
    <bos>
    0.65
     go
    0.45
     fjer
    0.44
    CE
    0.42
     VIAF
    0.40
    ให
    0.40
     zás
    0.39
    estr
    0.39
     huur
    0.39
    లాలు
    0.39
    Activations Density 0.924%

    No Known Activations