© 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. 3483
    Prev
    Next
    INDEX
    Explanations

    features of mediterranean culture referencing either location tags, architectural adjectives, or common words or syllables within placenames like 'La' and 'San'

    oai_token-act-pair · gemini-2.0-flash

    La

    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
     Chwiliwch
    -0.72
     Wikimedijinoj
    -0.71
    DockStyle
    -0.71
    uoco
    -0.68
     سكانية
    -0.66
     المعيارى
    -0.65
    entuh
    -0.63
    parsedMessage
    -0.62
    enterOuterAlt
    -0.61
    ampaikan
    -0.59
    POSITIVE LOGITS
     Приступљено
    0.46
    hatsu
    0.46
     sekali
    0.42
     R
    0.40
    avax
    0.40
     fatt
    0.40
    DataGridView
    0.40
    ículas
    0.40
    lavia
    0.40
    haden
    0.40
    Activations Density 0.384%

    No Known Activations