© 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. 2261
    Prev
    Next
    INDEX
    Explanations

    disjointed sections of text, frequently interspersed with quotation marks, numbers, and periods

    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
     but
    -2.77
    but
    -2.13
     tetapi
    -1.77
     pero
    -1.73
     nhưng
    -1.66
     namun
    -1.63
     however
    -1.53
     tapi
    -1.52
     BUT
    -1.52
    但是
    -1.45
    POSITIVE LOGITS
     TextAppearance
    0.44
     rangs
    0.42
    étique
    0.40
     فريبيس
    0.39
    âteau
    0.38
    AutoresizingMask
    0.38
     termine
    0.37
    onNext
    0.36
     glä
    0.36
    horabuena
    0.35
    Activations Density 17.465%

    No Known Activations