© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6042
    Prev
    Next
    INDEX
    Explanations

    capitalized words starting with "Ar"

    oai_token-act-pair · gemini-2.0-flash

    Ar

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     EconPapers
    -0.92
    SharedDtor
    -0.82
    expandindo
    -0.79
    EndGlobalSection
    -0.69
    AndEndTag
    -0.68
    ]-->
    -0.65
    الحياه
    -0.62
    InstanceState
    -0.62
     الحره
    -0.60
     Meksiku
    -0.60
    POSITIVE LOGITS
    rieta
    0.57
    nhold
    0.56
    deaux
    0.52
    INITY
    0.51
    genti
    0.51
    cepti
    0.50
    спита
    0.49
    gette
    0.49
    cana
    0.47
    gera
    0.47
    Activations Density 2.871%

    No Known Activations