© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3901
    Prev
    Next
    INDEX
    Explanations

    the word "to" preceded by certain other words

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     transfieras
    -0.74
    RenderAtEndOf
    -0.60
    Referanser
    -0.60
     volo
    -0.52
    DoubleQuotes
    -0.51
    DebuggerNonUser
    -0.51
    Jegyzetek
    -0.50
    bcryptjs
    -0.50
     suivants
    -0.48
    initializeApp
    -0.48
    POSITIVE LOGITS
     AspNetCore
    0.57
    CompleteListener
    0.56
     harp
    0.56
     snippetHide
    0.52
    Harp
    0.50
    ADVERTISEMENT
    0.50
    PRWEB
    0.49
     rub
    0.49
    HostException
    0.49
     Dynamite
    0.48
    Activations Density 1.205%

    No Known Activations