© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 4905
    Prev
    Next
    INDEX
    Explanations

    many common English words such as 'the', 'and', 'is', 'with', '1', '2', '3', '4', '5', 'to', 'be' and others of that nature

    oai_token-act-pair · 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
     Gates
    -0.69
    uments
    -0.66
    wheels
    -0.66
    ittles
    -0.63
    Gates
    -0.62
    tholes
    -0.61
    lapsingToolbar
    -0.61
    thanes
    -0.59
    illips
    -0.59
    foods
    -0.59
    POSITIVE LOGITS
     utafitiHapana
    0.59
    ConstraintMaker
    0.57
    IsContent
    0.57
     nakalista
    0.48
     lenker
    0.48
     arşivlendi
    0.48
     Nicol
    0.47
    MigrationBuilder
    0.45
     flashback
    0.43
     الاطلاع
    0.43
    Activations Density 41.728%

    No Known Activations