© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14863
    Prev
    Next
    INDEX
    Explanations

    words ending in "ov".

    oai_token-act-pair · gemini-2.0-flash

    technical terms or code components

    np_token-act-pair-logits · gpt-4o-mini

    Slavic names and topics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ########.
    -0.58
    setVerticalGroup
    -0.58
    Hosting
    -0.56
    országban
    -0.54
    <bos>
    -0.53
     GeoNames
    -0.53
    Gambas
    -0.50
    Discus
    -0.50
    ielsen
    -0.50
    verso
    -0.49
    POSITIVE LOGITS
    ImageContext
    0.68
     فريبيس
    0.56
    Clik
    0.51
     makeStyles
    0.50
    faker
    0.49
    ICH
    0.49
    PendingIntent
    0.48
    </thead>
    0.47
    XmlAccessType
    0.45
    stylers
    0.44
    Activations Density 0.449%

    No Known Activations