© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5568
    Prev
    Next
    INDEX
    Explanations

    phrases expressing negativity or disagreement, or references to family

    oai_token-act-pair · gemini-2.0-flash

    negative comments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    /**
    -0.58
    情
    -0.52
    anilla
    -0.46
     fiducia
    -0.46
    ToProps
    -0.45
    ighorn
    -0.44
     Feature
    -0.44
    expandindo
    -0.43
    følgelig
    -0.43
    ględ
    -0.42
    POSITIVE LOGITS
    Personendaten
    0.77
    IntoConstraints
    0.63
    RegistryLite
    0.61
    GOTREF
    0.58
    OGND
    0.57
     ModelExpression
    0.57
     MonoBehaviour
    0.56
    Portail
    0.56
    cienza
    0.56
    Put
    0.55
    Activations Density 4.743%

    No Known Activations