Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 13251
    Prev
    Next
    INDEX
    Explanations

    mentions of width, height and related properties in a coding context

    oai_token-act-pair · gemini-2.0-flash

    width

    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
    width
    -2.27
     width
    -2.20
     Width
    -2.05
    Width
    -2.03
     widths
    -1.91
    WIDTH
    -1.60
     WIDTH
    -1.60
     largeur
    -1.41
    widths
    -1.39
    宽度
    -1.33
    POSITIVE LOGITS
    staticmethod
    0.47
     Auft
    0.47
    INER
    0.44
     bad
    0.44
    besch
    0.44
    ziosi
    0.43
     bonne
    0.42
    textbackslash
    0.42
     speaker
    0.42
    ржа
    0.41
    Activations Density 1.088%

    No Known Activations