© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4094
    Prev
    Next
    INDEX
    Explanations

    words that are about a single person, object, or idea, especially in the context of more general comparison

    oai_token-act-pair · gemini-2.0-flash

    individual

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     and
    -0.60
    folgung
    -0.47
     con
    -0.44
     vid
    -0.44
    ).)
    -0.44
     Both
    -0.41
     The
    -0.41
     T
    -0.41
    ated
    -0.40
    </i>
    -0.40
    POSITIVE LOGITS
    LookAnd
    1.04
     resourceCulture
    1.02
    mybatisplus
    0.98
     beginnetje
    0.96
    ChildScrollView
    0.95
    ItemLayout
    0.95
     Partagez
    0.94
     &___
    0.93
     feroit
    0.92
     titolata
    0.91
    Activations Density 2.490%

    No Known Activations