© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11413
    Prev
    Next
    INDEX
    Explanations

    LaTeX or HTML code snippets

    oai_token-act-pair · gemini-2.0-flash

    specific formatting commands or code elements

    np_token-act-pair-logits · gpt-4o-mini

    brackets and UTF

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    )"),
    -0.75
    >",
    -0.71
    +#+#
    -0.71
    StoryboardSegue
    -0.67
    "]));
    -0.67
     Chwiliwch
    -0.66
    +#+
    -0.65
    '},
    -0.65
    LookAnd
    -0.65
    '])->
    -0.65
    POSITIVE LOGITS
    Bre
    0.47
    GeneratedValue
    0.46
    Break
    0.45
    ætte
    0.43
    ATE
    0.42
     aján
    0.42
     enak
    0.41
     gunung
    0.41
    ņu
    0.41
    tangentMode
    0.41
    Activations Density 0.557%

    No Known Activations