© 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. 5583
    Prev
    Next
    INDEX
    Explanations

    a wide variety of mostly function words, but also some descriptive words depending on the context

    oai_token-act-pair · gemini-2.0-flash

    Computer code

    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
    ItemBackground
    -0.63
    })$}
    -0.55
    </tfoot>
    -0.55
    "?>
    -0.53
     SwitchCompat
    -0.52
     ")");
    -0.50
    '")
    -0.50
     ziren
    -0.50
    '}),
    -0.49
    </thead>
    -0.49
    POSITIVE LOGITS
    tagHelperRunner
    0.72
    tvguidetime
    0.70
    SizeF
    0.68
    rungsseite
    0.65
    XmlRootElement
    0.61
     JpaRepository
    0.61
    SequentialGroup
    0.60
     cylinder
    0.57
     jspb
    0.56
     мәкал
    0.56
    Activations Density 8.806%

    No Known Activations