© 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. 14769
    Prev
    Next
    INDEX
    Explanations

    words indicating forward movement through time, especially adverbs and verbs related to progression

    oai_token-act-pair · gemini-2.0-flash

    finally

    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
     finally
    -0.81
    finally
    -0.78
     FINALLY
    -0.70
     finalmente
    -0.70
    FINALLY
    -0.69
     Finalmente
    -0.63
     Finally
    -0.62
     наконец
    -0.61
     eventually
    -0.60
    Finally
    -0.56
    POSITIVE LOGITS
    ArgsConstructor
    0.76
    visionnement
    0.66
    TagHelper
    0.66
    ubereitung
    0.65
    неопр
    0.63
    antMatchers
    0.62
    ########.
    0.61
    icznie
    0.61
    nables
    0.60
    mored
    0.59
    Activations Density 17.333%

    No Known Activations