© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8127
    Prev
    Next
    INDEX
    Explanations

    the suffix "fully" modifying a word

    oai_token-act-pair · gemini-2.0-flash

    fully

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Inſ
    -0.94
     Anſ
    -0.92
     faſt
    -0.90
     Monfieur
    -0.89
     Diſ
    -0.87
     Eſ
    -0.87
     Jefus
    -0.86
     itſelf
    -0.85
     Reſ
    -0.82
     myſelf
    -0.81
    POSITIVE LOGITS
    InjectAttribute
    1.26
     resourceCulture
    1.12
     AssemblyCulture
    1.10
     AssemblyTitle
    1.09
    帖最后由
    1.08
    +:+
    1.06
     GenerationType
    1.06
    AndEndTag
    1.06
     Chwiliwch
    1.02
    +#+#
    1.02
    Activations Density 2.080%

    No Known Activations