© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12822
    Prev
    Next
    INDEX
    Explanations

    words related to legal proceedings, code functions, villain names and music composers/artists.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    enderror
    -0.66
    Revenir
    -0.58
     елның
    -0.58
    MemoryWarning
    -0.51
     تانيه
    -0.51
    WebVitals
    -0.49
    onucle
    -0.48
    providedIn
    -0.47
    ніципалі
    -0.47
    icamente
    -0.47
    POSITIVE LOGITS
     autorytatywna
    0.80
    Datuak
    0.79
     defStyleAttr
    0.77
    resave
    0.71
     ErrInvalid
    0.68
    IUrlHelper
    0.66
    ValueStyle
    0.65
    ResponseWriter
    0.64
     PeEnEo
    0.64
     aveug
    0.63
    Activations Density 4.288%

    No Known Activations