© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7276
    Prev
    Next
    INDEX
    Explanations

    words related to shapes, sizes and quantities in a negative context

    oai_token-act-pair · gemini-2.0-flash

    Something important

    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
    SizeMode
    -0.82
     CreateTagHelper
    -0.77
    脚注の使い方
    -0.69
    findpost
    -0.68
    +#+#
    -0.67
    TagMode
    -0.66
    WireFormatLite
    -0.65
    IsContent
    -0.65
    ISupport
    -0.60
    enumii
    -0.60
    POSITIVE LOGITS
     forms
    0.58
    forms
    0.57
     wonders
    0.56
    iastes
    0.53
     figures
    0.52
     powers
    0.51
     marvels
    0.51
     rocks
    0.50
    Getenv
    0.50
    powers
    0.49
    Activations Density 12.351%

    No Known Activations