© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4320
    Prev
    Next
    INDEX
    Explanations

    the word "share", and also sometimes "child" and "dues"

    oai_token-act-pair · gemini-2.0-flash

    share

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Diſ
    -1.37
     Houſe
    -1.31
     Monfieur
    -1.24
     ſtate
    -1.21
     Reſ
    -1.18
     houſe
    -1.16
     Inſ
    -1.13
     Conſ
    -1.13
     pleaſure
    -1.12
     ſmall
    -1.09
    POSITIVE LOGITS
     bezeichneter
    1.07
     виправивши
    0.98
    Personendaten
    0.93
    ValueStyle
    0.93
    EndProject
    0.92
     disambiguazione
    0.91
    KommentareTeilen
    0.91
     estimés
    0.89
     Enix
    0.88
     CanadaChoose
    0.87
    Activations Density 1.518%

    No Known Activations