© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7151
    Prev
    Next
    INDEX
    Explanations

    reviews of outdoor recreational sites

    oai_token-act-pair · gemini-2.0-flash

    reviews of places

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    </b>
    -0.59
    </strong>
    -0.59
    certainly
    -0.57
    very
    -0.56
    at
    -0.54
    definitely
    -0.54
    as
    -0.52
    great
    -0.51
    RepeatedField
    -0.50
    !
    -0.50
    POSITIVE LOGITS
    WriteTagHelper
    0.79
    setVerticalGroup
    0.79
     незавершена
    0.72
    AddTagHelper
    0.68
    featureID
    0.65
    MessageTagHelper
    0.63
    principalTable
    0.63
    seteq
    0.63
     Wikimedijinoj
    0.62
    ]='\
    0.62
    Activations Density 13.149%

    No Known Activations