© 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
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 8838
    Prev
    Next
    INDEX
    Explanations

    content from scientific literature, legal documentation, and online surveys, which includes elements like citations, figures, opinions, URLs, measurements, and negative sentiment.

    oai_token-act-pair · gemini-2.0-flash

    Academic publications with citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    rungsseite
    -0.76
    RenderAtEndOf
    -0.69
     فريبيس
    -0.66
    RTHOOK
    -0.65
     مرئيه
    -0.65
     estekak
    -0.63
     esternos
    -0.63
     Públicas
    -0.61
    +#+#
    -0.59
    aarrggbb
    -0.57
    POSITIVE LOGITS
    principalTable
    0.57
    kku
    0.54
    \\\
    0.53
     محفوظة
    0.48
    ildes
    0.47
    atzung
    0.45
    ATUS
    0.43
    SpringBoot
    0.40
    providedIn
    0.40
     virtual
    0.40
    Activations Density 1.185%

    No Known Activations