© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11841
    Prev
    Next
    INDEX
    Explanations

    the word "finding" or phrases like "hence" and numbers or steps that imply a conclusion

    oai_token-act-pair · gemini-2.0-flash

    research findings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    NUMX
    -1.48
    ividual
    -1.22
    ratulations
    -1.18
    queryInterface
    -1.17
    styleType
    -1.15
    extAlignment
    -1.11
    iffance
    -1.09
     مرئيه
    -1.09
    olesale
    -1.05
    ########.
    -1.05
    POSITIVE LOGITS
    _
    0.83
    .
    0.82
    E
    0.78
    D
    0.78
    1
    0.77
    A
    0.75
    U
    0.75
    2
    0.74
    I
    0.74
    The
    0.71
    Activations Density 1.454%

    No Known Activations