© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12859
    Prev
    Next
    INDEX
    Explanations

    words related to expressing gratitude or providing assistance

    oai_token-act-pair · gemini-2.0-flash

    responses/wishes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ThroughAttribute
    -1.03
    rungsseite
    -1.02
    tagHelperRunner
    -0.96
    ScopeManager
    -0.91
    RenderAtEndOf
    -0.91
     ModelExpression
    -0.87
    DebuggerNonUser
    -0.85
     intptr
    -0.84
     BoxFit
    -0.82
    脚注の使い方
    -0.82
    POSITIVE LOGITS
     my
    0.58
    my
    0.46
     me
    0.45
    ↵↵
    0.42
     U
    0.41
    ,
    0.41
     traditional
    0.41
     p
    0.40
     sat
    0.40
     was
    0.40
    Activations Density 2.235%

    No Known Activations