© 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. 11022
    Prev
    Next
    INDEX
    Explanations

    table formatting characters and forward slashes

    oai_token-act-pair · gemini-2.0-flash

    ----------------

    np_max-act-logits · 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
     resourceCulture
    -0.86
     שוליים
    -0.73
    \{\\
    -0.70
    EndProject
    -0.68
     ComVisible
    -0.67
    awtextra
    -0.66
    Geplaatst
    -0.65
    存于互联网档案馆
    -0.64
    queryInterface
    -0.64
    ISupport
    -0.63
    POSITIVE LOGITS
    —
    1.79
    --
    1.73
    ---
    1.47
    ”—
    1.45
    –
    1.41
    )—
    1.40
    —-
    1.29
    ----
    1.22
    "—
    1.22
    "--
    1.21
    Activations Density 13.695%

    No Known Activations