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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7828
    Prev
    Next
    INDEX
    Explanations

    words starting with the prefix "de"

    oai_token-act-pair · gemini-2.0-flash

    de

    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
    SizeMode
    -0.84
     ModelExpression
    -0.78
    AndEndTag
    -0.77
     iprot
    -0.77
    ContentAsync
    -0.77
    __':
    -0.74
    __':
    -0.72
     saites
    -0.71
    SequentialGroup
    -0.68
    OGND
    -0.68
    POSITIVE LOGITS
    walled
    0.49
     Euse
    0.46
    wall
    0.44
    hitting
    0.44
     réfrig
    0.44
     voisins
    0.43
    agu
    0.43
     risol
    0.43
    WALL
    0.43
     vœ
    0.43
    Activations Density 3.856%

    No Known Activations