© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10330
    Prev
    Next
    INDEX
    Explanations

    descriptions of characters who paralyze or poison their targets.

    oai_token-act-pair · gemini-2.0-flash

    enemies and targets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     enemy
    -1.77
     opponent
    -1.60
    enemy
    -1.48
     Enemy
    -1.46
     opponents
    -1.45
    Enemy
    -1.44
     opposition
    -1.42
     enemies
    -1.41
     adversary
    -1.38
     adversaries
    -1.30
    POSITIVE LOGITS
    EN
    0.66
     EN
    0.63
     كومونز
    0.52
    μορ
    0.52
     en
    0.49
    ритори
    0.48
    apimachinery
    0.48
    FO
    0.47
    adar
    0.47
    en
    0.47
    Activations Density 2.252%

    No Known Activations