© 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. 12905
    Prev
    Next
    INDEX
    Explanations

    prepositions such as "to", "at", "in" and "for", often in the context of travel and time.

    oai_token-act-pair · gemini-2.0-flash

    going somewhere/something

    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
    TagMode
    -0.66
    IonicModule
    -0.52
     ***!
    -0.48
     park
    -0.46
    IComponent
    -0.46
    TagHelper
    -0.46
    */),
    -0.46
    UnsafeEnabled
    -0.45
     crossorigin
    -0.44
    AnchorStyles
    -0.43
    POSITIVE LOGITS
     Chwiliwch
    0.58
     éclairage
    0.56
    </tfoot>
    0.53
    ospor
    0.51
     étrangères
    0.51
     littéraire
    0.50
    MigrationBuilder
    0.50
    ActionCreators
    0.50
    wiz
    0.49
     marching
    0.49
    Activations Density 3.718%

    No Known Activations