© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13077
    Prev
    Next
    INDEX
    Explanations

    words that can function as adjectives.

    oai_token-act-pair · gemini-2.0-flash

    describes situations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     الحره
    -1.05
    NameInMap
    -0.88
     depend
    -0.77
     represent
    -0.74
    lequin
    -0.73
     propOrder
    -0.73
     look
    -0.72
    المناصب
    -0.72
    CROSSTALK
    -0.72
    MENTE
    -0.72
    POSITIVE LOGITS
     doesn
    1.03
     is
    1.02
     does
    0.84
     doesnt
    0.81
     appears
    0.79
     tends
    0.79
     belongs
    0.79
     hasn
    0.79
     knows
    0.76
     survives
    0.76
    Activations Density 17.304%

    No Known Activations