© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5822
    Prev
    Next
    INDEX
    Explanations

    phrases with numbers, symbols, or a mathematical style, and some conversational words

    oai_token-act-pair · gemini-2.0-flash

    $

    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
     instead
    -3.30
    instead
    -3.25
    Instead
    -3.19
     Instead
    -3.09
     Rather
    -2.81
     rather
    -2.80
    Rather
    -2.78
    rather
    -2.72
     вместо
    -2.52
     istället
    -2.52
    POSITIVE LOGITS
    })();
    0.52
    <bos>
    0.52
    endorff
    0.47
     ins
    0.47
    Basic
    0.47
    Ra
    0.45
    getDoctrine
    0.45
     reasonably
    0.45
     moderately
    0.45
    :"-"`
    0.44
    Activations Density 4.780%

    No Known Activations