© 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. 4810
    Prev
    Next
    INDEX
    Explanations

    words, usually prefixes, that are part of technical jargon

    oai_token-act-pair · gemini-2.0-flash

    cholesterol or scientific

    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
     PM
    -1.51
     DM
    -1.44
     CM
    -1.43
     RM
    -1.41
     FM
    -1.41
     BM
    -1.41
     NM
    -1.39
     SM
    -1.38
     CSM
    -1.35
     CCM
    -1.34
    POSITIVE LOGITS
    principalTable
    0.52
    rawtypes
    0.42
    ovatel
    0.42
     Serikat
    0.40
     Bengt
    0.40
    execSQL
    0.40
    şiv
    0.40
    RequiresApi
    0.38
     kasarigan
    0.37
    findpost
    0.37
    Activations Density 1.759%

    No Known Activations