© 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. 11001
    Prev
    Next
    INDEX
    Explanations

    sentences discussing how actions intended for one purpose may have undesired effects elsewhere

    oai_token-act-pair · gemini-2.0-flash

    negative effects

    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
     effect
    -3.09
    effect
    -2.98
     Effect
    -2.95
    Effect
    -2.80
     EFFECT
    -2.66
     Effects
    -2.55
     effects
    -2.53
    effects
    -2.41
    Effects
    -2.41
     EFFECTS
    -2.27
    POSITIVE LOGITS
    owohl
    0.49
    뀔
    0.42
    ريف
    0.41
    JFrame
    0.39
    뀐
    0.39
    esia
    0.39
     جغرافيا
    0.38
    çu
    0.38
    gne
    0.38
     fö
    0.37
    Activations Density 4.197%

    No Known Activations