© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15166
    Prev
    Next
    INDEX
    Explanations

    mentions of locations and legal residency

    oai_token-act-pair · gemini-2.0-flash

    Technical phrases

    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
     considérons
    -0.63
    LEncoder
    -0.59
    tisation
    -0.59
     IndexPath
    -0.56
    Personendaten
    -0.56
     communiquez
    -0.55
    tising
    -0.54
     setuptools
    -0.54
    olerance
    -0.53
    ymce
    -0.53
    POSITIVE LOGITS
    RenderAtEndOf
    0.65
    StoryboardSegue
    0.45
     Calder
    0.44
    ReusableCell
    0.44
    MENAFN
    0.44
    CppMethod
    0.43
    Tar
    0.43
     Cassini
    0.43
     Loeb
    0.41
     Caf
    0.41
    Activations Density 1.011%

    No Known Activations