© 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. 783
    Prev
    Next
    INDEX
    Explanations

    a mix of Spanish and English words related to programming logic, conditionals, and user understanding

    oai_token-act-pair · gemini-2.0-flash

    no

    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
     Мексичка
    -0.62
     utafitiHapana
    -0.59
     disambiguazione
    -0.55
    expandindo
    -0.54
    NUMX
    -0.53
    iastes
    -0.50
    Palmar
    -0.49
    μφωνα
    -0.47
     ProtoMessage
    -0.47
    Gweler
    -0.47
    POSITIVE LOGITS
     not
    0.77
    not
    0.76
    Not
    0.65
     typelib
    0.62
    NOT
    0.61
    +:+
    0.58
     Not
    0.57
    IsContent
    0.55
    шься
    0.53
    principalColumn
    0.52
    Activations Density 0.428%

    No Known Activations