© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12566
    Prev
    Next
    INDEX
    Explanations

    the tokens "Du", "Le", and "Lé" which are common in names

    oai_token-act-pair · gemini-2.0-flash

    Du

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ValueStyle
    -0.53
    DeleteBehavior
    -0.52
    __*/
    -0.51
     createSlice
    -0.50
     disambiguazione
    -0.49
    OrNil
    -0.48
     SEDS
    -0.48
    GEBURTSDATUM
    -0.47
     McFarland
    -0.47
    Diweddarwch
    -0.47
    POSITIVE LOGITS
     VIDEOTAPE
    0.61
     LoginComponent
    0.58
     Plage
    0.54
    maquilla
    0.53
    CROSSTALK
    0.52
     Fres
    0.52
    Посилання
    0.50
    ichtet
    0.48
     faid
    0.48
    istisches
    0.48
    Activations Density 1.530%

    No Known Activations