© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11557
    Prev
    Next
    INDEX
    Explanations

    words that are emphasized with underscores or are related to technical specifications

    oai_token-act-pair · gemini-2.0-flash

    markdown formatting

    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
    IMPORTED
    -0.57
     propOrder
    -0.51
    nvarchar
    -0.49
     Référence
    -0.48
     StatelessWidget
    -0.48
     utafiti
    -0.48
     HasFactory
    -0.46
    himovic
    -0.46
    arakhand
    -0.45
     OnInit
    -0.44
    POSITIVE LOGITS
    _
    2.70
    \_
    1.35
    _{
    1.13
    _*
    1.11
    _"
    1.10
    _$
    1.09
    _\
    1.05
    _'
    1.03
    _${
    1.01
    _%
    0.97
    Activations Density 9.388%

    No Known Activations