© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14792
    Prev
    Next
    INDEX
    Explanations

    scientific writing, especially physics or chemistry experiments

    oai_token-act-pair · gemini-2.0-flash

    An/an

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     an
    -0.73
     a
    -0.71
    ChildScrollView
    -0.50
     and
    -0.50
     referenties
    -0.48
     Paglinawan
    -0.43
     any
    -0.42
     all
    -0.42
    Nuorodos
    -0.41
     una
    -0.41
    POSITIVE LOGITS
    lapsingToolbar
    0.84
    awtextra
    0.82
    Diwedd
    0.70
     AssemblyVersion
    0.68
    poptosis
    0.65
    esModule
    0.65
     الاطلاع
    0.64
    ьаж
    0.64
     Polity
    0.64
    __":
    0.64
    Activations Density 10.039%

    No Known Activations