© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11756
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with legal opinions and official decisions.

    oai_token-act-pair · gemini-2.0-flash

    Formal/academic writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    1
    -1.51
    2
    -1.28
    3
    -1.22
    6
    -1.20
    4
    -1.18
    5
    -1.09
    9
    -1.05
    7
    -1.05
    8
    -1.03
    0
    -1.00
    POSITIVE LOGITS
    WithIOException
    1.09
    AddTagHelper
    1.08
     חיצוניים
    1.05
    findpost
    1.02
    matchCondition
    1.00
     Italijani
    0.99
     '\\;'
    0.98
    adpleegd
    0.97
    =$?
    0.97
    Vidite
    0.96
    Activations Density 6.268%

    No Known Activations