© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3821
    Prev
    Next
    INDEX
    Explanations

    negative assessments or descriptions of events, situations, or actions

    oai_token-act-pair · gemini-2.0-flash

    Forms of "to be"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    featureID
    -0.64
     CreateTagHelper
    -0.63
    UseVisualStyle
    -0.53
     estekak
    -0.49
    VIAF
    -0.48
     Paglinawan
    -0.47
    DebuggerNonUser
    -0.46
    Affirmed
    -0.46
    face
    -0.45
     face
    -0.44
    POSITIVE LOGITS
    rungsseite
    0.61
    HasAnnotation
    0.57
    StoryboardSegue
    0.57
    ävän
    0.56
    erweise
    0.54
     Efq
    0.53
    TagMode
    0.52
     gie
    0.52
    ch
    0.52
    AutoScale
    0.52
    Activations Density 3.963%

    No Known Activations