© 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. 5872
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "one" and pronouns

    oai_token-act-pair · gemini-2.0-flash

    sentences containing "nobody"

    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
    archiviato
    -0.72
    httphttps
    -0.69
    printStackTrace
    -0.69
     الحره
    -0.68
    findpost
    -0.67
     AspNetCore
    -0.63
     newOwner
    -0.63
     صوتيه
    -0.63
    StoryboardSegue
    -0.62
    #+#
    -0.60
    POSITIVE LOGITS
     }{@
    0.51
     rū
    0.49
     tư
    0.48
     نقط
    0.47
    besch
    0.47
     lägen
    0.47
     ✭✭
    0.45
    داشت
    0.45
     other
    0.45
     Shutter
    0.44
    Activations Density 7.434%

    No Known Activations