© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8701
    Prev
    Next
    INDEX
    Explanations

    the letter “V”

    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
     Partagez
    -0.73
    cheinend
    -0.62
    ----</
    -0.57
     Drit
    -0.57
    -------------</
    -0.57
     filial
    -0.57
    AddTagHelper
    -0.55
     contigo
    -0.54
     tenants
    -0.52
    ustimmung
    -0.52
    POSITIVE LOGITS
     utafitiHapana
    0.69
    WebVitals
    0.57
    ite
    0.54
    aughan
    0.52
    SourceChecksum
    0.52
    argas
    0.52
     OFDb
    0.49
    anden
    0.49
    ăn
    0.48
    HF
    0.48
    Activations Density 1.751%

    No Known Activations