© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2595
    Prev
    Next
    INDEX
    Explanations

    mentions of "Sandy" along with related words like "excuse" and "blame".

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    CloseOperation
    -0.73
    djangoproject
    -0.70
     IConfiguration
    -0.69
    enumi
    -0.63
     AssemblyCompany
    -0.62
    MigrationBuilder
    -0.60
    printStackTrace
    -0.58
     BorderRadius
    -0.58
     ['$
    -0.56
    UniformLocation
    -0.56
    POSITIVE LOGITS
     Hum
    0.49
     Pohl
    0.47
    Palindrome
    0.47
     fangs
    0.46
     cocoon
    0.45
    vių
    0.45
     Stirn
    0.44
    ыгана
    0.44
     caves
    0.43
    stärke
    0.43
    Activations Density 4.192%

    No Known Activations