© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8697
    Prev
    Next
    INDEX
    Explanations

    conditional statements often seen in software code and sentences that imply an interesting digression

    oai_token-act-pair · gemini-2.0-flash

    BUG

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    SequentialGroup
    -0.45
     onData
    -0.39
    łów
    -0.39
    alow
    -0.38
    DockStyle
    -0.38
    lwjgl
    -0.38
     accordingly
    -0.37
    ophon
    -0.37
     anyway
    -0.37
    enium
    -0.37
    POSITIVE LOGITS
    RegressionTest
    0.78
    MigrationBuilder
    0.77
    enderror
    0.70
    Espèce
    0.68
    ########.
    0.66
     nahilalakip
    0.66
    !("{}",
    0.66
     Meksiku
    0.65
    AndEndTag
    0.64
    новниш
    0.63
    Activations Density 0.674%

    No Known Activations