© 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. 3854
    Prev
    Next
    INDEX
    Explanations

    statements of the importance of something.

    oai_token-act-pair · gemini-2.0-flash

    technical jargon or keywords

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

    important

    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
    CompleteListener
    -0.57
     important
    -0.56
     المهم
    -0.53
     importance
    -0.52
    ornis
    -0.51
    ditch
    -0.50
    RenderAtEndOf
    -0.50
     المثال
    -0.50
    enziali
    -0.50
     vital
    -0.50
    POSITIVE LOGITS
    ArgsConstructor
    0.72
    engagent
    0.57
     مشين
    0.55
    WireFormatLite
    0.54
    AndEndTag
    0.51
    QMetaType
    0.51
    inae
    0.50
    OGND
    0.49
    riterien
    0.49
    enumi
    0.47
    Activations Density 11.755%

    No Known Activations