© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15669
    Prev
    Next
    INDEX
    Explanations

    the word "longer" and words or phrases around it that describe something decreasing or stopping.

    oai_token-act-pair · gemini-2.0-flash

    longer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Personendaten
    -1.19
    rungsseite
    -1.07
    ValueStyle
    -1.01
     AssemblyCulture
    -0.87
    utnik
    -0.86
     caufe
    -0.82
    出版年
    -0.81
    DebuggerStep
    -0.81
    OGND
    -0.80
     Italijanski
    -0.80
    POSITIVE LOGITS
     még
    0.47
     still
    0.44
    ↵↵
    0.41
     
    0.40
     noch
    0.39
    -
    0.38
    <bos>
    0.38
     jeszcze
    0.37
    ,
    0.36
     o
    0.36
    Activations Density 0.969%

    No Known Activations