© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10461
    Prev
    Next
    INDEX
    Explanations

    what appears to be somewhat malformed date references, mixed with some italian words

    oai_token-act-pair · 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
     DriverManager
    -0.68
     Normdatei
    -0.63
    ContentLoaded
    -0.59
     onPostExecute
    -0.58
    EndInit
    -0.58
    unmodifiable
    -0.57
    enterOuterAlt
    -0.57
    DoubleQuotes
    -0.57
     Souhaitez
    -0.57
    ativement
    -0.55
    POSITIVE LOGITS
    Personendaten
    0.49
    TagMode
    0.47
    úgó
    0.44
    BeginContext
    0.41
     expands
    0.40
     ExecuteAsync
    0.40
     bezeichneter
    0.39
     sẻ
    0.39
    createClass
    0.39
     bohat
    0.38
    Activations Density 0.341%

    No Known Activations