© 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. 5204
    Prev
    Next
    INDEX
    Explanations

    a combination of words indicating ordinal position, personal pronouns and statistics

    oai_token-act-pair · gemini-2.0-flash

    rankings

    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
     nine
    -1.11
     ninth
    -1.09
    nine
    -1.04
    Nine
    -1.04
     tenth
    -1.03
     Nine
    -1.02
     seventh
    -1.01
    Sixth
    -1.01
     seven
    -1.00
     fifth
    -1.00
    POSITIVE LOGITS
     
    1.13
     $
    0.61
     AssemblyCulture
    0.53
    ]--;
    0.52
    BindingResult
    0.52
    HideFlags
    0.50
    3
    0.44
    efits
    0.44
    ніципалі
    0.43
    ]+=
    0.42
    Activations Density 2.109%

    No Known Activations