© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 332
    Prev
    Next
    INDEX
    Explanations

    verbs and verb phrases that describe scientific observations or conclusions

    oai_token-act-pair · gemini-2.0-flash

    general concepts

    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
     mainly
    -2.64
     Mainly
    -2.53
     primarily
    -2.44
    primarily
    -2.30
    mainly
    -2.30
     Mostly
    -2.25
     mostly
    -2.23
    Mainly
    -2.19
     chiefly
    -2.19
    Mostly
    -2.11
    POSITIVE LOGITS
    جوايز
    0.56
    さま
    0.47
    viš
    0.47
    weisen
    0.46
    Exception
    0.46
    Throwable
    0.45
     pinulongan
    0.45
    ież
    0.45
    도
    0.44
    Palmar
    0.44
    Activations Density 3.949%

    No Known Activations