© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4120
    Prev
    Next
    INDEX
    Explanations

    words in Croatian related to confirmation and usage

    oai_token-act-pair · gemini-2.0-flash

    account confirmation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ]}>
    -0.50
    RegressionTest
    -0.49
    #+#
    -0.47
    setcounter
    -0.47
    witch
    -0.46
    }}{{
    -0.46
    )}>
    -0.45
     Hồ
    -0.45
     pourriez
    -0.44
    liothèque
    -0.43
    POSITIVE LOGITS
     ProtoMessage
    0.59
    LookAnd
    0.59
     ✭✭
    0.57
     nakalista
    0.56
    Życiorys
    0.55
     AppModule
    0.54
    Xaml
    0.54
     defaultstate
    0.51
     VizieR
    0.51
     ویکی‌پدیای
    0.50
    Activations Density 0.458%

    No Known Activations