© 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. 14817
    Prev
    Next
    INDEX
    Explanations

    temperature values

    oai_token-act-pair · gemini-2.0-flash

    Temperatures

    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
     HC
    -1.39
     WC
    -1.38
     EC
    -1.36
     RC
    -1.36
     LC
    -1.34
     BC
    -1.34
     TC
    -1.34
     ARC
    -1.31
     OC
    -1.31
     GC
    -1.30
    POSITIVE LOGITS
    DebuggerStep
    0.46
    WaitGroup
    0.45
    oplayer
    0.44
     Hummel
    0.42
    GEBRA
    0.40
    wollen
    0.40
    InputBorder
    0.39
     drapeau
    0.39
    पया
    0.39
    heimer
    0.39
    Activations Density 1.856%

    No Known Activations