© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 105
    Prev
    Next
    INDEX
    Explanations

    phrases that include conjunctions and demonstrative pronouns.

    oai_token-act-pair · gemini-2.0-flash

    Technical explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     للمعارف
    -0.74
    VersionUID
    -0.67
    SequentialGroup
    -0.59
     tartalomajánló
    -0.56
    unknownFields
    -0.56
     ddelweddau
    -0.56
    leistungs
    -0.54
    UpInside
    -0.54
    batore
    -0.53
    hasOwnProperty
    -0.52
    POSITIVE LOGITS
     nakalista
    0.62
     Superhost
    0.51
     exitosa
    0.49
    +:+
    0.48
    Décès
    0.48
     shewn
    0.46
     absc
    0.45
     Confira
    0.44
     Scrolls
    0.44
     miracles
    0.44
    Activations Density 2.026%

    No Known Activations