© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15844
    Prev
    Next
    INDEX
    Explanations

    the word "level" as it pertains to liquid

    oai_token-act-pair · gemini-2.0-flash

    level

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    GraphicsUnit
    -1.01
    <bos>
    -0.91
     GenerationType
    -0.88
    printStackTrace
    -0.87
     CreateTagHelper
    -0.81
    UserScript
    -0.81
     Houſe
    -0.79
     Efq
    -0.79
    ſelf
    -0.78
     houſe
    -0.78
    POSITIVE LOGITS
     nélkül
    0.60
    etlen
    0.54
    $;
    0.51
     précédente
    0.50
     snabb
    0.49
    eless
    0.49
     ($
    0.46
     цвят
    0.45
    )\}$
    0.45
    (":");
    0.45
    Activations Density 0.237%

    No Known Activations