© 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. 14057
    Prev
    Next
    INDEX
    Explanations

    words that are verbs conjugated in 1st person plural, and Spanish/Croatian mobile-app programming-related words

    oai_token-act-pair · gemini-2.0-flash

    Non-English language

    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
    ItemBackground
    -0.78
     TestBed
    -0.77
    PhysRevLett
    -0.76
    GraphicsUnit
    -0.75
    InjectAttribute
    -0.74
    PreferredItem
    -0.71
     незавершена
    -0.71
    AndEndTag
    -0.71
     SwitchCompat
    -0.65
     виправивши
    -0.65
    POSITIVE LOGITS
    renos
    0.53
    CROSSTALK
    0.45
     convention
    0.45
     externally
    0.42
    out
    0.41
     frequently
    0.40
     Convention
    0.40
     strongly
    0.40
    ваний
    0.39
     ins
    0.39
    Activations Density 23.514%

    No Known Activations