© 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. 14351
    Prev
    Next
    INDEX
    Explanations

    past-tense auxiliary verbs like "was", "were", and "did" followed by a second verb

    oai_token-act-pair · gemini-2.0-flash

    Past tense

    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
     continued
    -0.49
    continued
    -0.47
    AddWithValue
    -0.45
     المعيارى
    -0.44
     lighter
    -0.43
    pona
    -0.43
     حک
    -0.43
    ксу
    -0.42
     ondes
    -0.42
     Follow
    -0.42
    POSITIVE LOGITS
     estimés
    0.85
    writeFieldEnd
    0.77
     Audiodateien
    0.77
    RenderAtEndOf
    0.77
     consultato
    0.68
    Források
    0.65
    Portale
    0.64
    archiviato
    0.64
     مشين
    0.63
    TextSpan
    0.63
    Activations Density 0.555%

    No Known Activations