© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3878
    Prev
    Next
    INDEX
    Explanations

    the word "series" and words referring to body parts or scientific/medical labels

    oai_token-act-pair · gemini-2.0-flash

    series

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    +#+#
    -1.21
     SqlCommand
    -1.14
    AndEndTag
    -1.09
    verwijspagina
    -1.09
    endpush
    -1.06
     unknownFields
    -1.04
     vPvB
    -1.01
    IUrlHelper
    -1.00
     transfieras
    -0.98
    XmlAccessType
    -0.98
    POSITIVE LOGITS
    s
    0.67
    ↵↵
    0.63
     the
    0.61
    es
    0.58
    ing
    0.57
     and
    0.57
    I
    0.55
    is
    0.55
     He
    0.54
     I
    0.54
    Activations Density 2.950%

    No Known Activations