© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10869
    Prev
    Next
    INDEX
    Explanations

    emotionally charged commentary on political figures or situations

    oai_token-act-pair · gemini-2.0-flash

    past tense actions related to shooting or striking

    np_token-act-pair-logits · gpt-4o-mini

    Taking shots/attacks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    évaluateur
    -0.77
    UserScript
    -0.57
     Shakspeare
    -0.55
     constellations
    -0.55
    ρεύ
    -0.54
     Jefus
    -0.53
     habet
    -0.53
     Dijo
    -0.52
     Bioaccumulative
    -0.52
     itſelf
    -0.52
    POSITIVE LOGITS
     dig
    0.84
     shots
    0.84
     shot
    0.77
     aim
    0.73
     j
    0.68
    shot
    0.67
     swipe
    0.66
    shots
    0.65
     Shots
    0.63
     attacks
    0.63
    Activations Density 1.850%

    No Known Activations