© 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. 10805
    Prev
    Next
    INDEX
    Explanations

    prepositions and words that often appear near them, and also past tense verbs

    oai_token-act-pair · gemini-2.0-flash

    Descriptions or instructions

    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
    TagMode
    -0.88
    RenderAtEndOf
    -0.88
    ANTLR
    -0.72
     चीज़ों
    -0.65
    DeleteBehavior
    -0.65
     صوتيه
    -0.64
    IVEREF
    -0.63
    oplayer
    -0.62
    TagHelper
    -0.61
    SharedDtor
    -0.60
    POSITIVE LOGITS
    ніципалі
    0.50
     hus
    0.49
    supporting
    0.47
     Guides
    0.47
    venir
    0.46
     supporting
    0.45
    feldt
    0.45
     Protecting
    0.44
     JpaRepository
    0.44
     Arrondissement
    0.44
    Activations Density 4.199%

    No Known Activations