© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9637
    Prev
    Next
    INDEX
    Explanations

    slightly shortened versions of words that would otherwise start with "com"

    oai_token-act-pair · gemini-2.0-flash

    Comp

    np_max-act · gemini-2.0-flash

    Comp Method used: 1 — because MAX_ACTIVATING_TOKENS are variations of "Comp"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     Sus
    -1.05
     Ret
    -0.98
     Cri
    -0.93
     Rec
    -0.91
     Emp
    -0.90
     Sup
    -0.90
     Res
    -0.89
     Pla
    -0.89
     Acc
    -0.88
     Past
    -0.88
    POSITIVE LOGITS
     quæ
    1.10
     auffi
    1.06
     Milán
    0.97
     Noviembre
    0.96
     Settembre
    0.96
     Ottobre
    0.95
     Constitucional
    0.94
     Febrero
    0.94
     Parigi
    0.93
     ainfi
    0.92
    Activations Density 7.655%

    No Known Activations