© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 14214
    Prev
    Next
    INDEX
    Explanations

    code and scientific measurements.

    oai_token-act-pair · gemini-2.0-flash

    Chemical experimental descriptions

    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
     GL
    -1.41
     ML
    -1.35
     SL
    -1.34
     RL
    -1.33
     TL
    -1.31
     HL
    -1.31
     BL
    -1.30
     Bl
    -1.30
     DL
    -1.27
    Gl
    -1.26
    POSITIVE LOGITS
    GraphicsUnit
    0.44
    indahkan
    0.43
    methoxy
    0.42
    čenje
    0.42
     doInBackground
    0.41
     onOptions
    0.41
    +#+#
    0.41
    setOnAction
    0.40
    eriksaan
    0.40
    TextAppearance
    0.39
    Activations Density 1.626%

    No Known Activations