© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13697
    Prev
    Next
    INDEX
    Explanations

    terms related to projectile weaponry and photography

    oai_token-act-pair · gemini-2.0-flash

    shooting/camera focus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     erwartet
    -0.49
    rictive
    -0.45
     liever
    -0.43
    Witam
    -0.43
     démarches
    -0.43
     nied
    -0.42
    ệc
    -0.42
     diferencial
    -0.41
    Actualmente
    -0.41
    想的
    -0.40
    POSITIVE LOGITS
    ThroughAttribute
    0.83
     EClass
    0.69
     thrones
    0.61
     '{@
    0.61
     Erg
    0.61
    akaian
    0.60
     HasFactory
    0.59
    曖昧さ回避
    0.58
    וויק
    0.58
     Macca
    0.57
    Activations Density 2.636%

    No Known Activations