© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14100
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to laws, rules, ownership, and suitability

    oai_token-act-pair · gemini-2.0-flash

    legality and appropriateness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     modelAndView
    -0.59
    TintMode
    -0.56
    ByEmail
    -0.54
    છ
    -0.54
    actéristi
    -0.53
    actéristique
    -0.52
    IBLES
    -0.51
    virons
    -0.51
    iguous
    -0.51
     margin
    -0.49
    POSITIVE LOGITS
     صوتيه
    0.59
    IntoConstraints
    0.57
    Thinking
    0.56
    Activité
    0.55
    expandindo
    0.54
     Pingback
    0.53
    Související
    0.53
    CppMethod
    0.53
     ordina
    0.52
    ReusableCell
    0.52
    Activations Density 0.523%

    No Known Activations