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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11483
    Prev
    Next
    INDEX
    Explanations

    LaTeX code

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    enumi
    -0.70
     bakgrund
    -0.65
     nakalista
    -0.60
     varandra
    -0.58
     vérit
    -0.58
    ningss
    -0.55
    bbene
    -0.54
     säll
    -0.54
     adultes
    -0.54
     orizz
    -0.53
    POSITIVE LOGITS
    TagMode
    0.64
    rungsseite
    0.60
    parsedMessage
    0.59
    expandindo
    0.56
     PARSER
    0.54
    EndInit
    0.54
    InitVars
    0.53
    !")
    0.52
    ukone
    0.52
    stander
    0.52
    Activations Density 1.612%

    No Known Activations