© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6251
    Prev
    Next
    INDEX
    Explanations

    phrases expressing desire or intent, often negative

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    帖最后由
    -0.74
     auroit
    -0.68
     وتسجيلات
    -0.66
     feroit
    -0.65
     étoient
    -0.65
     avoient
    -0.61
     ainfi
    -0.59
     finnas
    -0.56
     ElementRef
    -0.56
    +#+#
    -0.56
    POSITIVE LOGITS
     chance
    0.69
    AddAttribute
    0.59
     even
    0.57
    oredCriteria
    0.56
    ographe
    0.55
    getDoctrine
    0.54
     linkovi
    0.54
     risk
    0.52
     Lordships
    0.51
    sizeCache
    0.51
    Activations Density 2.606%

    No Known Activations