© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12769
    Prev
    Next
    INDEX
    Explanations

    words related to emotional connection, concern, and support

    oai_token-act-pair · gemini-2.0-flash

    Care and concern

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     CreateTagHelper
    -1.01
    
    -0.96
    IVEREF
    -0.91
     lenker
    -0.88
    RenderAtEndOf
    -0.88
     فريبيس
    -0.86
    Clik
    -0.84
    ########.
    -0.83
    IntoConstraints
    -0.78
     NSCoder
    -0.76
    POSITIVE LOGITS
    <bos>
    0.45
     dataSnapshot
    0.44
     visits
    0.41
    ib
    0.41
     vett
    0.40
    com
    0.40
    S
    0.40
    comp
    0.39
    hasNext
    0.39
    O
    0.38
    Activations Density 1.430%

    No Known Activations