© 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. 7407
    Prev
    Next
    INDEX
    Explanations

    language related to advice and recommendations

    oai_token-act-pair · gemini-2.0-flash

    terms related to manufacturers and production

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

    Technical/instructional content

    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
    blockList
    -0.50
     GoogleFonts
    -0.49
    XmlAccessorType
    -0.46
    TimeUnit
    -0.42
    日閲覧
    -0.41
    manes
    -0.41
    qrstuvwxyz
    -0.41
    kwds
    -0.41
    ziert
    -0.40
     везде
    -0.40
    POSITIVE LOGITS
     manufacturers
    0.70
     مرئيه
    0.65
     Efq
    0.64
    providedIn
    0.60
     Hersteller
    0.60
     juſ
    0.60
     manufacturer
    0.57
     recommendations
    0.57
     محفوظة
    0.57
     ammat
    0.56
    Activations Density 4.685%

    No Known Activations