© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12796
    Prev
    Next
    INDEX
    Explanations

    variations of the verb "can" and the pronoun "you"

    oai_token-act-pair · gemini-2.0-flash

    they

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     
    -0.47
    上了
    -0.42
     looks
    -0.39
    里
    -0.37
     डाल
    -0.37
    里的
    -0.35
     ör
    -0.35
     ACT
    -0.35
    gång
    -0.35
     #
    -0.34
    POSITIVE LOGITS
     propOrder
    1.13
    GraphicsUnit
    1.04
    parsedMessage
    1.03
     <<<<<<<<<<<<<<
    1.02
     дописавши
    0.99
    脚注の使い方
    0.92
    EDEFAULT
    0.92
    +#+#
    0.89
     Мексичка
    0.88
    AddTagHelper
    0.88
    Activations Density 2.936%

    No Known Activations