© 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. 11975
    Prev
    Next
    INDEX
    Explanations

    a mix of arabic names, numbers, code, and words related to expressing or implying

    oai_token-act-pair · gemini-2.0-flash

    foreign 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_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
    island
    -0.45
     island
    -0.45
     TO
    -0.44
     tre
    -0.44
     co
    -0.44
     to
    -0.44
    getC
    -0.44
     at
    -0.43
     c
    -0.43
    onge
    -0.43
    POSITIVE LOGITS
     Efq
    1.10
     Theſe
    1.00
     Monfieur
    0.96
     ſeveral
    0.95
     Jefus
    0.94
     auffi
    0.93
     pleaſure
    0.90
     quæ
    0.88
     ainfi
    0.88
     étoient
    0.87
    Activations Density 0.101%

    No Known Activations