© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12144
    Prev
    Next
    INDEX
    Explanations

    legal and numerical references, often citations and statistics

    oai_token-act-pair · gemini-2.0-flash

    Non-English tokens

    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
    -
    -1.13
    \-
    -0.63
    ‐
    -0.61
    ®-
    -0.57
    -&
    -0.57
    -"+
    -0.57
    –
    -0.57
    ‑
    -0.55
    -<
    -0.55
    -),
    -0.53
    POSITIVE LOGITS
     ২০১
    0.75
    MemoryWarning
    0.71
    Portail
    0.71
     ۱۶
    0.71
     estekak
    0.71
     ۱۳۹
    0.70
     CreateTagHelper
    0.70
     ২০
    0.69
    enderror
    0.69
     ۱۴۰۰
    0.68
    Activations Density 8.611%

    No Known Activations