© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4162
    Prev
    Next
    INDEX
    Explanations

    pronouns

    oai_token-act-pair · gemini-2.0-flash

    negative contractions

    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
     InputDecoration
    -0.84
    abestanden
    -0.73
     endwhile
    -0.72
     kaarangay
    -0.71
     disambiguazione
    -0.67
     désolés
    -0.67
     beginnetje
    -0.65
    rungsseite
    -0.65
    ViewFeatures
    -0.63
    Geplaatst
    -0.62
    POSITIVE LOGITS
     haven
    1.11
     hasn
    1.06
     hadn
    0.87
     havent
    0.75
     Haven
    0.75
    haven
    0.71
    Haven
    0.62
     belum
    0.59
     chua
    0.57
     chưa
    0.55
    Activations Density 0.994%

    No Known Activations