© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12751
    Prev
    Next
    INDEX
    Explanations

    mentions of interpersonal relationships like couples, families, and lovers.

    oai_token-act-pair · gemini-2.0-flash

    interpersonal relationships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    principalTable
    -0.80
     navideña
    -0.63
     vérit
    -0.60
     ambientale
    -0.60
    omiast
    -0.59
    EndProject
    -0.58
     titolata
    -0.58
     fallu
    -0.57
    richTextPanel
    -0.57
    RTSC
    -0.56
    POSITIVE LOGITS
    sieme
    0.52
    guan
    0.48
    citep
    0.48
    dafx
    0.48
    ONIC
    0.47
    titian
    0.45
    ング
    0.44
    digm
    0.43
     Fut
    0.43
    Моло
    0.43
    Activations Density 1.449%

    No Known Activations