© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3287
    Prev
    Next
    INDEX
    Explanations

    negative statements about people, along with associated words, like "is absolute", "s hypocritical", or "really strange".

    oai_token-act-pair · gemini-2.0-flash

    Negative/critical statements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     CreateTagHelper
    -0.49
    RenderAtEndOf
    -0.48
    rangle
    -0.45
    ```
    -0.45
    shadowOpacity
    -0.45
    getLong
    -0.44
    cast
    -0.43
    expédition
    -0.42
    setNum
    -0.42
     durs
    -0.41
    POSITIVE LOGITS
    UnitTesting
    0.81
    odiment
    0.70
     autorytatywna
    0.70
    Tikang
    0.66
    /******/
    0.63
    TestingModule
    0.61
    StructEnd
    0.61
    Carriera
    0.60
    Tiet
    0.59
    EDEFAULT
    0.57
    Activations Density 1.687%

    No Known Activations