© 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. 13200
    Prev
    Next
    INDEX
    Explanations

    statements of intent and ability using auxiliary verbs

    oai_token-act-pair · gemini-2.0-flash

    Limitations and negations

    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
     pair
    -0.63
    #+#
    -0.61
     team
    -0.57
     فريبيس
    -0.55
    libft
    -0.55
    team
    -0.53
    MENAFN
    -0.53
     Paglinawan
    -0.52
     function
    -0.51
     link
    -0.50
    POSITIVE LOGITS
    PreferredItem
    0.75
     disambiguazione
    0.59
     GenerationType
    0.59
    ArgsConstructor
    0.59
     loose
    0.59
     waste
    0.57
    telep
    0.56
    UserScript
    0.55
    ên
    0.54
     miss
    0.54
    Activations Density 6.462%

    No Known Activations