© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15325
    Prev
    Next
    INDEX
    Explanations

    words or phrases that suggest conflict or problems, including health problems and potentially coding errors.

    oai_token-act-pair · gemini-2.0-flash

    negative connotations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ]")]
    -0.59
    комен
    -0.48
    amen
    -0.47
    الحياه
    -0.47
    KEYCODE
    -0.47
     незавершена
    -0.46
    ⁠
    -0.45
    COUVER
    -0.44
    ariato
    -0.44
     kol
    -0.44
    POSITIVE LOGITS
    PerformLayout
    0.67
     tartalomajánló
    0.66
     Extragalactic
    0.62
    HostException
    0.60
     bauer
    0.58
    UVWXYZ
    0.58
     itſelf
    0.57
    Antibodies
    0.57
     Susie
    0.54
     Parece
    0.53
    Activations Density 5.785%

    No Known Activations