© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11855
    Prev
    Next
    INDEX
    Explanations

    words related to locations, objects and events in the world

    oai_token-act-pair · gemini-2.0-flash

    Foreign adjectives

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Infórmanos
    -1.28
     BoxFit
    -1.11
    Portale
    -1.09
     disambiguazione
    -1.09
    Geplaatst
    -1.08
    
    -1.07
    RegistryLite
    -1.06
    migrationBuilder
    -1.06
    WebElementEntity
    -1.06
    AnchorStyles
    -1.04
    POSITIVE LOGITS
     piccole
    0.57
     antiguas
    0.50
     buone
    0.48
     antigas
    0.47
     pequenas
    0.46
     pequeñas
    0.46
     semplici
    0.45
     antigos
    0.44
     precedenti
    0.43
     antiguos
    0.43
    Activations Density 4.543%

    No Known Activations