© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3341
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate repetition, improvement, or forward motion

    oai_token-act-pair · gemini-2.0-flash

    repeated words and phrases

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

    again

    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
     again
    -2.42
    Again
    -2.31
     Again
    -2.28
    again
    -2.25
     AGAIN
    -1.98
     novamente
    -1.77
     nuevamente
    -1.63
     опять
    -1.60
     wieder
    -1.55
    AGAIN
    -1.53
    POSITIVE LOGITS
     compito
    0.49
     braccio
    0.47
     recientes
    0.43
    Task
    0.41
    ,
    0.40
     cielos
    0.39
     közé
    0.39
     resolução
    0.39
    scp
    0.38
     inizio
    0.38
    Activations Density 4.069%

    No Known Activations