© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6600
    Prev
    Next
    INDEX
    Explanations

    words and concepts related to negative aspects of humanity, such as violence, evil, and death.

    oai_token-act-pair · gemini-2.0-flash

    negative/chaotic situations

    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
     estekak
    -0.61
     Dernière
    -0.59
     EconPapers
    -0.59
    thebibliography
    -0.57
    انتهای
    -0.56
    ynchrotron
    -0.53
     vortex
    -0.52
     vortices
    -0.52
     Warp
    -0.51
     المعيارى
    -0.50
    POSITIVE LOGITS
     newOwner
    0.60
    Carriera
    0.55
    ”]
    0.52
    ]?
    0.48
    "]:
    0.47
    __*/
    0.47
    ”?
    0.46
     continúas
    0.46
     <<=
    0.45
    ()?
    0.45
    Activations Density 32.031%

    No Known Activations