© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14355
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to physical textures

    oai_token-act-pair · gemini-2.0-flash

    soft

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     soft
    -2.61
    Soft
    -2.44
     Soft
    -2.42
    soft
    -2.42
     SOFT
    -2.17
     softer
    -2.05
    SOFT
    -2.02
     softness
    -2.00
    軟
    -1.59
     soften
    -1.52
    POSITIVE LOGITS
    Scalars
    0.48
    
    0.46
     TestBed
    0.45
    Respuesta
    0.44
    SOUNDBITE
    0.44
    cier
    0.42
     mote
    0.42
     dep
    0.42
     convertView
    0.42
     çe
    0.42
    Activations Density 11.357%

    No Known Activations