© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11001
    Prev
    Next
    INDEX
    Explanations

    descriptions of items for sales

    oai_token-act-pair · gemini-2.0-flash

    condition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     «
    -0.53
     sur
    -0.49
     ar
    -0.45
    ,
    -0.45
     e
    -0.44
    bein
    -0.43
     Ar
    -0.43
     ‘
    -0.43
    -
    -0.42
    :
    -0.42
    POSITIVE LOGITS
     itſelf
    1.14
     ſever
    1.12
     purpoſe
    1.08
     myſelf
    1.06
     Diſ
    1.01
     <=",
    1.01
     Anſ
    1.00
     Houſe
    0.98
     ſtate
    0.98
     betweenstory
    0.97
    Activations Density 0.459%

    No Known Activations