© 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. 1999
    Prev
    Next
    INDEX
    Explanations

    instances where someone needs to do something

    oai_token-act-pair · gemini-2.0-flash

    expressions of need or assistance

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

    need

    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
    writeFieldEnd
    -0.97
    AutoScaleMode
    -0.85
    Espèce
    -0.83
    InjectAttribute
    -0.81
    AddTagHelper
    -0.81
    UnusedPrivate
    -0.79
    UrlResolution
    -0.77
     GenerationType
    -0.77
    mobileqq
    -0.75
    RenderAtEndOf
    -0.75
    POSITIVE LOGITS
     to
    1.02
     a
    0.81
     help
    0.61
     assistance
    0.59
     an
    0.55
     another
    0.54
     support
    0.53
     permission
    0.53
     lots
    0.50
     plenty
    0.49
    Activations Density 1.882%

    No Known Activations