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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12777
    Prev
    Next
    INDEX
    Explanations

    prepositions and articles, sometimes in conjunction with location-oriented words

    oai_token-act-pair · gemini-2.0-flash

    anatomical parts or positions

    np_token-act-pair-logits · gpt-4o-mini

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    EndContext
    -0.53
     propOrder
    -0.49
    стюм
    -0.46
     maschile
    -0.45
    yelitis
    -0.45
    positivos
    -0.44
     ItemStack
    -0.43
    ânsito
    -0.43
    ValueGeneration
    -0.43
    Cordialement
    -0.42
    POSITIVE LOGITS
     back
    0.99
     bottom
    0.91
     base
    0.82
     backside
    0.79
    bottom
    0.77
     side
    0.75
     front
    0.73
     top
    0.73
     outside
    0.73
     sides
    0.73
    Activations Density 0.954%

    No Known Activations