© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9335
    Prev
    Next
    INDEX
    Explanations

    text repeating in the document

    oai_token-act-pair · gemini-2.0-flash

    varied text snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    +#+
    -0.92
    ftagPool
    -0.74
    aarrggbb
    -0.69
    ContentAsync
    -0.64
     resourceCulture
    -0.62
    ">{{$
    -0.61
    UnusedPrivate
    -0.60
     ddelweddau
    -0.58
    #
    -0.57
     onCreateView
    -0.55
    POSITIVE LOGITS
    DebuggerNonUser
    0.54
    AutoScaleMode
    0.52
     userSchema
    0.47
    ADN
    0.45
     kvar
    0.45
    writeFieldEnd
    0.45
    liğini
    0.44
     propre
    0.43
     facilite
    0.43
     demanded
    0.43
    Activations Density 1.407%

    No Known Activations