© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15083
    Prev
    Next
    INDEX
    Explanations

    mentions related to physical actions or specific locations.

    oai_token-act-pair · gemini-2.0-flash

    long

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    PerformLayout
    -0.59
    InteropServices
    -0.56
    IVEREF
    -0.55
    坞
    -0.54
    GeneratedCode
    -0.53
    InSection
    -0.49
    AndView
    -0.47
    ็จ
    -0.46
    derung
    -0.46
    SharedDtor
    -0.45
    POSITIVE LOGITS
     long
    2.16
    long
    1.82
     LONG
    1.55
    Long
    1.52
     Long
    1.45
    LONG
    1.41
     longer
    1.16
     longue
    1.14
     longo
    1.13
     longest
    1.12
    Activations Density 5.780%

    No Known Activations