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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5257
    Prev
    Next
    INDEX
    Explanations

    the string "lat"

    oai_token-act-pair · gemini-2.0-flash

    tokens starting with 'Lat'

    np_token-act-pair-logits · gpt-4o-mini

    lat

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     advance
    -0.55
    amani
    -0.52
     tens
    -0.49
    NDICE
    -0.48
    CCIÓN
    -0.47
    zema
    -0.47
    oltà
    -0.46
    UCIÓN
    -0.46
    AMAN
    -0.45
     entgegen
    -0.45
    POSITIVE LOGITS
    tvguidetime
    0.73
    ViewImports
    0.71
    ⓧ
    0.67
    enumi
    0.63
    providedIn
    0.61
     informée
    0.59
    }>;
    0.59
    TestingModule
    0.58
    Jereo
    0.58
    ########.
    0.57
    Activations Density 0.421%

    No Known Activations