© 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. 9520
    Prev
    Next
    INDEX
    Explanations

    statements of agreement or correctness.

    oai_token-act-pair · gemini-2.0-flash

    agreement/correctness

    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
     propOrder
    -1.06
    SourceChecksum
    -1.02
    ########.
    -0.96
    OGND
    -0.88
    thâu
    -0.88
    StructEnd
    -0.84
    mybatisplus
    -0.83
    expandindo
    -0.82
    migrationBuilder
    -0.82
    قایناق‌لار
    -0.81
    POSITIVE LOGITS
     I
    0.42
    walde
    0.42
     göre
    0.41
    re
    0.41
    puta
    0.37
     shouldn
    0.36
    .
    0.36
     high
    0.36
    b
    0.36
     because
    0.35
    Activations Density 0.652%

    No Known Activations