© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12116
    Prev
    Next
    INDEX
    Explanations

    discusses conditions, but focuses on health

    oai_token-act-pair · gemini-2.0-flash

    Code/Technical snippets

    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
    Personensuche
    -0.73
    Personendaten
    -0.69
     المعيارى
    -0.69
    enterOuterAlt
    -0.67
    verwijspagina
    -0.66
    setVerticalGroup
    -0.65
    AddTagHelper
    -0.65
    
    -0.64
     gynhyrchwyd
    -0.63
    PreExecute
    -0.62
    POSITIVE LOGITS
    eira
    0.47
     nullable
    0.47
    entingan
    0.46
    django
    0.43
    VersionUID
    0.43
     emot
    0.42
    decided
    0.42
    ByDefault
    0.41
    alom
    0.40
    ędz
    0.40
    Activations Density 0.809%

    No Known Activations