© 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. 11656
    Prev
    Next
    INDEX
    Explanations

    verbs and adjectives related to solving problems

    oai_token-act-pair · gemini-2.0-flash

    addressing problems/respectful behavior

    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
    havior
    -0.50
    nessed
    -0.48
     injury
    -0.46
     autoradio
    -0.46
    mybatisplus
    -0.45
    Biografia
    -0.45
    Aiheesta
    -0.45
    seck
    -0.44
    ListFragment
    -0.44
    getClassName
    -0.44
    POSITIVE LOGITS
    GEBURTSDATUM
    0.70
     Италијани
    0.63
     وتسجيلات
    0.60
     للاسماء
    0.59
    kháu
    0.58
    ConstraintMaker
    0.57
    __*/
    0.56
    LookAnd
    0.56
    tonsoft
    0.55
    Espèce
    0.54
    Activations Density 1.352%

    No Known Activations