© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14292
    Prev
    Next
    INDEX
    Explanations

    the word "in" followed by a word indicating some condition or situation

    oai_token-act-pair · gemini-2.0-flash

    in

    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
    SourceChecksum
    -0.91
    tagHelperRunner
    -0.77
     متعلقه
    -0.68
     مرئيه
    -0.62
     if
    -0.62
     vengan
    -0.59
     venga
    -0.56
     navideño
    -0.56
     navideños
    -0.55
    Билгалдахарш
    -0.53
    POSITIVE LOGITS
     case
    3.58
    case
    3.03
    Case
    2.84
     Case
    2.78
     CASE
    2.42
     cases
    2.41
    CASE
    2.39
     caso
    2.22
     Cases
    2.09
    cases
    2.08
    Activations Density 1.821%

    No Known Activations