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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14485
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "out" that describe something ending or becoming known.

    oai_token-act-pair · gemini-2.0-flash

    out

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    LookAnd
    -1.06
     AssemblyCulture
    -1.02
    AddTagHelper
    -0.90
    tagHelperRunner
    -0.82
    GenerationType
    -0.80
     صوتيه
    -0.77
     beginnetje
    -0.74
     мәкал
    -0.73
    AddHtmlAttribute
    -0.72
    bibfield
    -0.71
    POSITIVE LOGITS
    char
    0.53
     into
    0.50
    li
    0.49
     of
    0.49
    .
    0.46
     char
    0.46
    ster
    0.46
    ge
    0.43
     in
    0.43
    set
    0.42
    Activations Density 10.257%

    No Known Activations