© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7309
    Prev
    Next
    INDEX
    Explanations

    words that are parts of proper names or that represent quantities or logical conditions

    oai_token-act-pair · gemini-2.0-flash

    Technical context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    }))
    -0.50
    aksikan
    -0.47
    '])){
    -0.44
    ifndef
    -0.43
     sabes
    -0.43
    denly
    -0.42
     iconst
    -0.41
    ")));
    -0.41
    ldr
    -0.40
    }));
    -0.40
    POSITIVE LOGITS
    ValueStyle
    1.17
    Personendaten
    0.64
    Rujuakan
    0.63
    RectangleBorder
    0.62
    AsUp
    0.57
    ElementException
    0.56
     Allí
    0.55
    gameserver
    0.54
    zzleHttp
    0.54
    minecraftforge
    0.54
    Activations Density 8.620%

    No Known Activations