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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8317
    Prev
    Next
    INDEX
    Explanations

    legal language related to citizenship and naturalization

    oai_token-act-pair · gemini-2.0-flash

    scientific/technical publications

    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
     con
    -1.16
     com
    -1.08
     combina
    -1.04
     interpreta
    -1.02
     conversa
    -1.01
     transporta
    -1.01
     accom
    -1.00
     concentra
    -0.99
     organiza
    -0.98
     profes
    -0.98
    POSITIVE LOGITS
     acoper
    1.21
     picioare
    1.16
     piele
    1.13
     maș
    1.12
     prieten
    1.07
     scurt
    1.06
     noastre
    1.05
     argint
    1.04
     păr
    1.03
     băr
    1.00
    Activations Density 4.770%

    No Known Activations