© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3269
    Prev
    Next
    INDEX
    Explanations

    fragments of words or beginnings of words without regard to context.

    oai_token-act-pair · gemini-2.0-flash

    fam

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     pinulongan
    -0.94
     estekak
    -0.86
    IsContent
    -0.84
    rungsseite
    -0.81
    enumi
    -0.81
    TagMode
    -0.80
     Signalez
    -0.79
     Normdatei
    -0.79
    EndContext
    -0.77
    MigrationBuilder
    -0.77
    POSITIVE LOGITS
     ties
    0.61
     imp
    0.47
     Ties
    0.46
    fek
    0.43
     es
    0.41
    rods
    0.41
    Hes
    0.41
    setOptions
    0.40
     Kug
    0.40
    Notices
    0.39
    Activations Density 0.796%

    No Known Activations