© 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. 14052
    Prev
    Next
    INDEX
    Explanations

    Italian words and names in a variety of contexts, often related to events or media

    oai_token-act-pair · gemini-2.0-flash

    multiple languages

    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
     itſelf
    -0.57
     juſ
    -0.56
     ſen
    -0.52
    enumii
    -0.52
     pleaſure
    -0.50
     faſt
    -0.50
     themſelves
    -0.48
     himſelf
    -0.48
     preſent
    -0.47
     purpoſe
    -0.47
    POSITIVE LOGITS
    SPATH
    0.69
    OGND
    0.68
    CCESS
    0.66
    Hozzáférés
    0.63
     disambiguazione
    0.62
     Qui
    0.61
    glie
    0.60
     Quell
    0.60
     Quest
    0.60
     Sul
    0.59
    Activations Density 1.010%

    No Known Activations