© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7263
    Prev
    Next
    INDEX
    Explanations

    the letter "V" (possibly in the context of code)

    oai_token-act-pair · gemini-2.0-flash

    V

    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
     doInBackground
    -0.75
    مصادر
    -0.59
    versiti
    -0.57
     JpaRepository
    -0.55
    setupUi
    -0.54
    :✨
    -0.53
    ForTesting
    -0.49
     holotype
    -0.49
    avoie
    -0.49
     GENERATED
    -0.48
    POSITIVE LOGITS
    Portale
    0.60
    illus
    0.52
    ue
    0.50
    elo
    0.50
    ivid
    0.49
     succ
    0.47
    iol
    0.47
    pe
    0.47
    illas
    0.46
    ào
    0.46
    Activations Density 8.808%

    No Known Activations