© 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. 12858
    Prev
    Next
    INDEX
    Explanations

    text related to Q&A, code snippets and asking for help in advance.

    oai_token-act-pair · gemini-2.0-flash

    Questions and answers

    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
    émission
    -0.57
    intérieur
    -0.56
    ReusableCell
    -0.55
    équipement
    -0.54
    échelle
    -0.53
    extérieur
    -0.51
    étranger
    -0.49
    moveToFirst
    -0.49
    entraînement
    -0.49
    humanité
    -0.48
    POSITIVE LOGITS
     APD
    0.88
     AH
    0.87
     Ay
    0.87
     Ahl
    0.86
     Af
    0.85
     AX
    0.85
     Adi
    0.85
     Aker
    0.85
     AW
    0.85
     AD
    0.85
    Activations Density 9.832%

    No Known Activations