© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1040
    Prev
    Next
    INDEX
    Explanations

    german words and verbs

    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
    CloseOperation
    -0.35
    titleMargin
    -0.29
     uniformly
    -0.28
    </tfoot>
    -0.27
    లాలు
    -0.24
     ""],
    -0.24
    <tfoot>
    -0.22
    twimg
    -0.22
     course
    -0.22
    ńskiego
    -0.21
    POSITIVE LOGITS
     propOrder
    0.62
     Roskov
    0.60
    iedenen
    0.54
    ädig
    0.53
    SourceChecksum
    0.52
     conosce
    0.52
     olvido
    0.50
    gangenen
    0.50
    ädigung
    0.50
    riebene
    0.49
    Activations Density 3.531%

    No Known Activations