© 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. 13841
    Prev
    Next
    INDEX
    Explanations

    a person's observation or involvement in an event that affects them

    oai_token-act-pair · gemini-2.0-flash

    observation of an event

    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
    offsetof
    -0.76
     يتيمه
    -0.74
     виправивши
    -0.71
     дописавши
    -0.69
    writeFieldEnd
    -0.68
    Personendaten
    -0.67
    NewGuid
    -0.62
     <=",
    -0.60
    AutoScaleMode
    -0.60
     useStyles
    -0.60
    POSITIVE LOGITS
     double
    0.60
    Double
    0.53
     Double
    0.52
    double
    0.50
     privilegi
    0.44
    Doubles
    0.44
     doubled
    0.43
    씩
    0.43
    estroyer
    0.43
    Domaine
    0.42
    Activations Density 1.860%

    No Known Activations