© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13035
    Prev
    Next
    INDEX
    Explanations

    proper nouns or titles, especially those denoting individuals or businesses, in close proximity to verbs or conjunctions.

    oai_token-act-pair · gemini-2.0-flash

    People in companies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     utafitiHapana
    -0.66
    ISupport
    -0.61
    Geplaatst
    -0.59
    kháu
    -0.59
     protoimpl
    -0.59
     ReactDOM
    -0.57
    Демографія
    -0.57
     disambiguazione
    -0.57
    Jereo
    -0.57
     Préférences
    -0.56
    POSITIVE LOGITS
    principalColumn
    0.51
    Altri
    0.50
    stwie
    0.44
     struck
    0.44
    ίες
    0.43
    >({
    0.43
    ]^{-
    0.43
    </table>
    0.42
    autoload
    0.42
    ield
    0.41
    Activations Density 3.025%

    No Known Activations