© 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. 6442
    Prev
    Next
    INDEX
    Explanations

    steps, instructions, and lists, often signified by arrows and commas

    oai_token-act-pair · gemini-2.0-flash

    Filenames

    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
     esternos
    -0.80
     EconPapers
    -0.68
    enumii
    -0.66
     ComVisible
    -0.59
     Magna
    -0.57
    lorette
    -0.55
     snippetHide
    -0.54
    AndEndTag
    -0.54
    ">—
    -0.53
    లాలు
    -0.53
    POSITIVE LOGITS
     garanzia
    0.56
     Documents
    0.54
    matchCondition
    0.53
     documents
    0.51
    Documents
    0.49
    ägg
    0.49
     port
    0.48
     Audiodateien
    0.47
     scheda
    0.47
     Files
    0.46
    Activations Density 11.941%

    No Known Activations