© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11253
    Prev
    Next
    INDEX
    Explanations

    words similar to "bad" or the suffix "or"

    oai_token-act-pair · gemini-2.0-flash

    bly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    abestanden
    -1.00
    InjectAttribute
    -0.98
     InputDecoration
    -0.95
    SerializedSize
    -0.92
    Personendaten
    -0.88
    хьтан
    -0.82
    GraphicsUnit
    -0.82
    WithIOException
    -0.80
    CloseOperation
    -0.79
    ArgsConstructor
    -0.78
    POSITIVE LOGITS
    <bos>
    0.76
     bad
    0.59
     good
    0.59
     best
    0.58
     terrible
    0.52
     horrible
    0.49
    Best
    0.49
    Good
    0.48
     malos
    0.48
     mauvaise
    0.47
    Activations Density 0.972%

    No Known Activations