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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11965
    Prev
    Next
    INDEX
    Explanations

    words related to optional product features and product numbers

    oai_token-act-pair · gemini-2.0-flash

    product specifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    oredCriteria
    -0.79
     Roskov
    -0.71
    )"),
    -0.71
    "]),
    -0.68
    verwijspagina
    -0.68
     <=",
    -0.67
    ')),
    -0.67
    '},
    -0.66
    EndGlobalSection
    -0.66
    ']),
    -0.66
    POSITIVE LOGITS
    drawImage
    0.49
    zęd
    0.47
     prod
    0.47
    esModule
    0.45
    CreateMap
    0.45
    basicConfig
    0.43
     correlation
    0.43
    anwal
    0.42
    ⏭
    0.41
     correlates
    0.41
    Activations Density 0.764%

    No Known Activations