© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14062
    Prev
    Next
    INDEX
    Explanations

    LaTeX code for defining tables and arrays

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Roskov
    -0.95
    Personendaten
    -0.88
    Tikang
    -0.78
    NameInMap
    -0.73
    featureID
    -0.68
     EconPapers
    -0.68
    Diwedd
    -0.65
    OGND
    -0.65
    tagHelperRunner
    -0.65
    NOPQRST
    -0.64
    POSITIVE LOGITS
    ue
    0.46
     PICTOGRAM
    0.43
    up
    0.43
    wau
    0.43
    bac
    0.42
    clr
    0.42
    dra
    0.41
    el
    0.41
     Forumite
    0.41
    gan
    0.40
    Activations Density 0.732%

    No Known Activations