© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12439
    Prev
    Next
    INDEX
    Explanations

    phone numbers

    oai_token-act-pair · gemini-2.0-flash

    numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     CreateTagHelper
    -0.98
    tagHelperRunner
    -0.85
     '\\;'
    -0.84
    WriteBarrier
    -0.84
     beginnetje
    -0.82
    تقاوى
    -0.82
     Réponses
    -0.78
    COUVER
    -0.78
    ArgsConstructor
    -0.77
     nahilalakip
    -0.77
    POSITIVE LOGITS
     
    0.67
    1
    0.59
    3
    0.56
    2
    0.52
    5
    0.49
    4
    0.48
    zess
    0.45
    7
    0.44
    0
    0.43
     Ota
    0.43
    Activations Density 3.818%

    No Known Activations