© 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. 10713
    Prev
    Next
    INDEX
    Explanations

    the word "of," sometimes "about," and often in the context of time passing or opinions

    oai_token-act-pair · gemini-2.0-flash

    late

    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
    </tfoot>
    -0.62
     يتيمه
    -0.61
    XmlAccessType
    -0.58
    Diweddarwch
    -0.58
    новништво
    -0.50
     Exactos
    -0.50
     MyBatis
    -0.49
    MemoryWarning
    -0.49
    química
    -0.49
    来歴
    -0.47
    POSITIVE LOGITS
     late
    3.11
    Late
    2.55
    late
    2.55
     Late
    2.50
     LATE
    2.31
    LATE
    1.95
     spät
    1.20
    lates
    1.15
     позд
    1.08
     lato
    1.06
    Activations Density 2.379%

    No Known Activations