© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10079
    Prev
    Next
    INDEX
    Explanations

    descriptions of powers, abilities, and transformations of characters, often in a science fiction or fantasy context.

    oai_token-act-pair · gemini-2.0-flash

    Character special abilities

    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
    RenderAtEndOf
    -0.76
     ویکی‌پدیا
    -0.76
    Revenir
    -0.65
    initializeApp
    -0.63
    Hochspringen
    -0.61
     متعلقه
    -0.60
     esternos
    -0.60
    GEBURTSDATUM
    -0.59
     BrowserModule
    -0.58
    onAttach
    -0.58
    POSITIVE LOGITS
    いえ
    0.48
    XmlElement
    0.45
     createSprite
    0.44
    čka
    0.44
    OrBuilder
    0.43
     ".";
    0.43
    ̣n
    0.43
     projets
    0.42
    pects
    0.42
    čky
    0.42
    Activations Density 5.958%

    No Known Activations