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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14024
    Prev
    Next
    INDEX
    Explanations

    the word 'a' preceded by a verb implying creation

    oai_token-act-pair · gemini-2.0-flash

    Articles "a" and "an"

    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
     experimenter
    -0.52
    }];
    -0.51
     khe
    -0.50
    |}{$
    -0.50
    transQ
    -0.49
    もしれない
    -0.47
    DeleteBehavior
    -0.46
    frc
    -0.46
    StructEnd
    -0.46
    styleUrls
    -0.45
    POSITIVE LOGITS
    DockStyle
    0.97
    AnchorStyles
    0.86
    bootstrapcdn
    0.85
     BoxFit
    0.70
    InputBorder
    0.68
     AssemblyCulture
    0.62
    \{\\
    0.62
     ivelany
    0.62
    ArgsConstructor
    0.60
    ChildScrollView
    0.59
    Activations Density 1.803%

    No Known Activations