© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10664
    Prev
    Next
    INDEX
    Explanations

    words pertaining to people giving their opinions

    oai_token-act-pair · gemini-2.0-flash

    comment/post

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    AddTagHelper
    -0.92
     EconPapers
    -0.84
    IVEREF
    -0.81
    bootstrapcdn
    -0.81
     виправивши
    -0.79
     utafitiHapana
    -0.78
    protoimpl
    -0.77
     poffible
    -0.76
    createCanvas
    -0.74
    UnusedPrivate
    -0.72
    POSITIVE LOGITS
    ↵↵↵
    0.46
    ::::::::
    0.45
     */
    0.45
    </blockquote>
    0.45
    ↵↵
    0.45
    isière
    0.43
     couvercle
    0.43
    **********/
    0.43
    <bos>
    0.42
    </h5>
    0.42
    Activations Density 1.258%

    No Known Activations