© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5924
    Prev
    Next
    INDEX
    Explanations

    technical information about nickel ore processing

    oai_token-act-pair · gemini-2.0-flash

    metal extraction

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    謀
    -0.43
     alimentaria
    -0.42
    <bos>
    -0.42
    Qed
    -0.40
    RenderAtEndOf
    -0.39
    Troll
    -0.39
     plataforma
    -0.39
     platforms
    -0.38
     מש
    -0.38
     plataformas
    -0.38
    POSITIVE LOGITS
     Référence
    0.92
    ########.
    0.82
     ExecuteAsync
    0.82
    دانشنامهٔ
    0.73
     AssemblyVersion
    0.70
    principalTable
    0.68
     CreateTagHelper
    0.67
    OGND
    0.66
    iprot
    0.66
     AssemblyTitle
    0.66
    Activations Density 0.485%

    No Known Activations