© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 6130
    Prev
    Next
    INDEX
    Explanations

    code and non-English language.

    oai_token-act-pair · gemini-2.0-flash

    Spanish text and programming

    np_max-act-logits · gemini-2.0-flash

    Spanish

    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_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
    RenderAtEndOf
    -0.85
    ValueStyle
    -0.73
     متعلقه
    -0.71
     Normdatei
    -0.71
    AndEndTag
    -0.69
    Portale
    -0.65
    uação
    -0.63
    ContentAsync
    -0.62
    InitVars
    -0.61
    يكب
    -0.60
    POSITIVE LOGITS
     sin
    1.07
     Sin
    0.88
    Sin
    0.87
    sin
    0.83
     SIN
    0.75
     sins
    0.63
    SIN
    0.60
     streaks
    0.54
     recevrez
    0.52
     sinned
    0.52
    Activations Density 0.472%

    No Known Activations