© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15088
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "ID"

    oai_token-act-pair · gemini-2.0-flash

    identifiers or labels

    np_token-act-pair-logits · gpt-4o-mini

    Id

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    AddTagHelper
    -0.80
     NSCoder
    -0.77
    RegistryLite
    -0.70
    SupportActionBar
    -0.68
    PDOException
    -0.68
    IsMutable
    -0.68
     TestBed
    -0.67
     AttributeSet
    -0.67
     AssemblyTitle
    -0.66
     autorytatywna
    -0.65
    POSITIVE LOGITS
    TestTools
    0.57
     riduzione
    0.43
    let
    0.41
     scatola
    0.38
    @
    0.38
    zani
    0.38
    näm
    0.38
    concatenate
    0.37
     proceed
    0.37
     Reduction
    0.37
    Activations Density 1.105%

    No Known Activations