© 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
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8092
    Prev
    Next
    INDEX
    Explanations

    a mix of underscores, medical terms involving 'cha', employment talk, and words with spelling errors

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     téléphonique
    -0.73
    ?”.
    -0.73
    soort
    -0.65
    .”.
    -0.63
    IsContent
    -0.62
    )”.
    -0.61
    ”。
    -0.60
    !”.
    -0.59
    hoea
    -0.58
    }}{(
    -0.58
    POSITIVE LOGITS
     currently
    0.56
     essentially
    0.53
     către
    0.53
     تضيفلها
    0.52
     originally
    0.51
     initially
    0.51
     considered
    0.51
     being
    0.50
     MonoBehaviour
    0.50
     admittedly
    0.50
    Activations Density 5.629%

    No Known Activations