© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5377
    Prev
    Next
    INDEX
    Explanations

    the word "impression" and words related to types or variants

    oai_token-act-pair · gemini-2.0-flash

    impression

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    vot
    -0.57
    hubaneswar
    -0.57
    DialogInterface
    -0.54
     quæ
    -0.53
    spaceBetween
    -0.52
     viewType
    -0.51
     tristesse
    -0.51
     bisous
    -0.50
     jer
    -0.50
     omnia
    -0.50
    POSITIVE LOGITS
    <bos>
    1.21
    oredCriteria
    0.80
    ]=>
    0.74
    encodeWith
    0.70
     Савезне
    0.68
    IUrlHelper
    0.66
    ècie
    0.65
    SourceChecksum
    0.64
    OGND
    0.63
     دیکھیے
    0.63
    Activations Density 0.802%

    No Known Activations