© 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. 4454
    Prev
    Next
    INDEX
    Explanations

    words related to arguments or negative interactions especially involving giving something back

    oai_token-act-pair · gemini-2.0-flash

    back

    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
     pageable
    -0.49
    wijl
    -0.42
    ım
    -0.42
    ,:);
    -0.42
     Hentet
    -0.41
    hbase
    -0.40
    pendi
    -0.40
    Reducers
    -0.40
    mockMvc
    -0.39
    FieldBuilder
    -0.39
    POSITIVE LOGITS
     back
    3.56
    back
    2.78
    Back
    2.73
     Back
    2.66
     BACK
    2.52
    BACK
    2.38
    backs
    1.87
    バック
    1.76
     backs
    1.76
     tillbaka
    1.61
    Activations Density 2.874%

    No Known Activations