© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14848
    Prev
    Next
    INDEX
    Explanations

    expressions of caring or not caring about something

    oai_token-act-pair · gemini-2.0-flash

    care

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     pleaſure
    -0.73
    Cyfeiriadau
    -0.69
     ſta
    -0.64
     ſmall
    -0.64
     reaſon
    -0.61
     purpoſe
    -0.61
     ſtate
    -0.60
     Majefty
    -0.60
     fhew
    -0.59
     Reſ
    -0.59
    POSITIVE LOGITS
    migrationBuilder
    0.69
    tagHelperRunner
    0.58
    BoxShadow
    0.55
    TagHelper
    0.55
     autorytatywna
    0.54
    存于互联网档案馆
    0.54
     unknownFields
    0.54
    StructEnd
    0.51
     "..\..\
    0.50
     "..\..\..\
    0.50
    Activations Density 0.504%

    No Known Activations