© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7823
    Prev
    Next
    INDEX
    Explanations

    words related to necessity, possibly indicating that something is important within the provided context .

    oai_token-act-pair · gemini-2.0-flash

    negative words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ReusableCell
    -0.65
    lankton
    -0.56
     '\\;'
    -0.56
    انيف
    -0.54
     insuffisamment
    -0.52
    OPSIS
    -0.51
    .'</
    -0.51
    ingeki
    -0.50
     hâte
    -0.50
    __))
    -0.49
    POSITIVE LOGITS
    Pyx
    0.66
     propOrder
    0.56
    Portail
    0.54
    TestBed
    0.54
    oredCriteria
    0.52
    <bos>
    0.51
    RegressionTest
    0.48
    كويكب
    0.47
     best
    0.47
    tonsoft
    0.46
    Activations Density 0.812%

    No Known Activations