© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13535
    Prev
    Next
    INDEX
    Explanations

    different types of sharks in the water

    oai_token-act-pair · gemini-2.0-flash

    specialized technical terms or jargon

    np_token-act-pair-logits · gpt-4o-mini

    Fish and sharks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    didSet
    -0.60
     NDEBUG
    -0.47
    boleh
    -0.46
    heide
    -0.46
     Reim
    -0.45
     برانيه
    -0.45
     throat
    -0.44
    landt
    -0.44
     paces
    -0.43
    dying
    -0.43
    POSITIVE LOGITS
    RetentionPolicy
    0.68
    KURZBESCHREIBUNG
    0.61
     الاطلاع
    0.58
    Cyfarwyddwr
    0.56
    ExecuteReader
    0.56
     estekak
    0.56
     informée
    0.56
     QtCore
    0.54
    DockStyle
    0.54
    OOTDTY
    0.52
    Activations Density 1.513%

    No Known Activations