© 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. 11209
    Prev
    Next
    INDEX
    Explanations

    french verbs

    oai_token-act-pair · gemini-2.0-flash

    French language

    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
    WithIOException
    -0.64
    Je
    -0.56
    ystis
    -0.52
     Je
    -0.52
    je
    -0.50
     Shrine
    -0.49
     Meksiku
    -0.48
     ozone
    -0.48
     je
    -0.48
     shrine
    -0.48
    POSITIVE LOGITS
    providedIn
    0.69
    MemoryWarning
    0.68
    DeleteBehavior
    0.60
    erdings
    0.50
    insee
    0.50
     indisponible
    0.49
    ρεύ
    0.47
    مقاله
    0.47
    ∶
    0.46
    ERTE
    0.46
    Activations Density 0.623%

    No Known Activations