© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4968
    Prev
    Next
    INDEX
    Explanations

    capitalized words, especially nouns, related to committees or boards, and the possessive "'s".

    oai_token-act-pair · gemini-2.0-flash

    Public meetings/announcements

    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
    sax
    -0.50
    FailureListener
    -0.48
     Ouverture
    -0.46
     plan
    -0.44
    kében
    -0.41
     Irvin
    -0.41
     informé
    -0.40
    Население
    -0.40
     vog
    -0.40
     sic
    -0.40
    POSITIVE LOGITS
    ScopeManager
    0.65
    NameInMap
    0.64
    +#+#
    0.64
     Bater
    0.59
     guantes
    0.59
    __(/*!
    0.58
    DockStyle
    0.57
    SharedDtor
    0.57
    MENAFN
    0.57
    TypedDataSet
    0.57
    Activations Density 9.399%

    No Known Activations