© 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. 4640
    Prev
    Next
    INDEX
    Explanations

    California place names, code syntax, and abbreviated author names

    oai_token-act-pair · gemini-2.0-flash

    code-related

    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
     VA
    -1.50
     VC
    -1.48
     VB
    -1.44
     VV
    -1.44
     V
    -1.42
    VC
    -1.41
     VF
    -1.38
     VT
    -1.38
     Va
    -1.37
     Vi
    -1.36
    POSITIVE LOGITS
     disambiguazione
    0.50
     darb
    0.40
    Erreferentziak
    0.40
    äki
    0.38
    jske
    0.38
     mė
    0.38
     nė
    0.37
     dė
    0.36
     Exteriores
    0.36
    Tikang
    0.35
    Activations Density 1.518%

    No Known Activations