© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8310
    Prev
    Next
    INDEX
    Explanations

    words related to preparation with a focus on emotional or internal states.

    oai_token-act-pair · gemini-2.0-flash

    preparation phrases

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

    prepare

    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
     AssemblyCompany
    -0.44
     honor
    -0.43
     Mors
    -0.42
    VertexAttrib
    -0.42
    urllib
    -0.41
     Establish
    -0.41
     dise
    -0.41
     Stardust
    -0.40
     հղումներ
    -0.40
     seizing
    -0.40
    POSITIVE LOGITS
    __);
    0.71
    ImageContext
    0.67
    RenderAtEndOf
    0.63
     MessageBoxIcon
    0.62
     for
    0.60
    écnicas
    0.60
     avoient
    0.59
    MemoryWarning
    0.58
     sacré
    0.57
     myſelf
    0.57
    Activations Density 12.411%

    No Known Activations