© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6634
    Prev
    Next
    INDEX
    Explanations

    statements of difficulty and logical reasoning

    oai_token-act-pair · gemini-2.0-flash

    differentiating

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ⓧ
    -0.70
    पया
    -0.60
     يتيمه
    -0.59
    InputBorder
    -0.56
    Geplaatst
    -0.52
    istoitu
    -0.48
     Baillargeon
    -0.47
    BagLayout
    -0.46
    adaptiveStyles
    -0.45
    MarshalTo
    -0.45
    POSITIVE LOGITS
     distinguishing
    1.09
     identification
    1.09
     distinguish
    1.05
     differentiating
    1.05
     determination
    1.02
     Identification
    1.02
     identifying
    1.00
     differentiate
    0.99
     distinguishes
    0.98
     identify
    0.96
    Activations Density 2.667%

    No Known Activations