© 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
    2. Gemma-2-2B
    3. 6-GEMMASCOPE-TRANSCODER-16K
    4. 15750
    Prev
    Next
    INDEX
    Explanations

    words indicating conditional phrases or potential problems

    oai_token-act-pair · gemini-2.0-flash

    Customer service/relationship issues

    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
     <<<<<<<<<<<<<<
    -0.76
     ويكيپيديا
    -0.73
     @"/
    -0.72
    הערות
    -0.71
     '\\;'
    -0.66
    ագրություններ
    -0.65
    protoimpl
    -0.65
    styleUrls
    -0.63
    ResumeLayout
    -0.62
     RouterModule
    -0.62
    POSITIVE LOGITS
     any
    0.56
     Any
    0.50
     Harcourt
    0.50
     apapun
    0.49
    Any
    0.48
     anything
    0.47
    ときは
    0.47
     qualquer
    0.46
    際は
    0.46
     orice
    0.46
    Activations Density 1.864%

    No Known Activations