© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 517
    Prev
    Next
    INDEX
    Explanations

    mentions of train and test ratios in data analysis

    oai_token-act-pair · gemini-2.0-flash

    ratio and test

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    mpto
    -0.61
    قایناقلار
    -0.57
    Composable
    -0.54
    ifeng
    -0.54
    ngOn
    -0.51
    Hozzáférés
    -0.51
     références
    -0.51
    Portail
    -0.50
    utches
    -0.49
    ждествен
    -0.49
    POSITIVE LOGITS
     Exacts
    0.63
    évaluateur
    0.61
    MigrationBuilder
    0.60
    GEBURTSDATUM
    0.60
    zoned
    0.50
    StructEnd
    0.50
     proportions
    0.49
     rozho
    0.48
     виправивши
    0.48
     PhpStorm
    0.48
    Activations Density 1.954%

    No Known Activations