© 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
    2. Gemma-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 9667
    Prev
    Next
    INDEX
    Explanations

    the word "file", and the topic seems to be related to moving files from one directory to another

    oai_token-act-pair · gemini-2.0-flash

    file

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    h
    -0.46
     extended
    -0.46
     concept
    -0.44
    j
    -0.41
    def
    -0.41
     best
    -0.40
    </td>
    -0.39
    pe
    -0.39
    知る
    -0.39
    t
    -0.39
    POSITIVE LOGITS
     BorderSide
    0.86
     tslint
    0.85
    extAlignment
    0.82
    tagHelperRunner
    0.82
     HasFactory
    0.81
    expandindo
    0.80
    Попис
    0.78
    NUMX
    0.77
    quelize
    0.76
    fromCharCode
    0.75
    Activations Density 0.865%

    No Known Activations