© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11692
    Prev
    Next
    INDEX
    Explanations

    passive sentence constructions related to official statements.

    oai_token-act-pair · gemini-2.0-flash

    news/commentary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     faim
    -0.47
    bibitem
    -0.47
     honlap
    -0.46
    recie
    -0.46
    wapV
    -0.45
     falda
    -0.45
    –¿
    -0.45
     door
    -0.45
    <bos>
    -0.44
    Übersetzung
    -0.44
    POSITIVE LOGITS
     AssemblyVersion
    0.63
    άσ
    0.60
    GraphicsUnit
    0.59
     gynhyrchwyd
    0.59
    AutoScale
    0.58
    providedIn
    0.58
     slightest
    0.56
    nvarchar
    0.55
     articulate
    0.55
    aarrggbb
    0.55
    Activations Density 1.602%

    No Known Activations