© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11663
    Prev
    Next
    INDEX
    Explanations

    a mix of sentence fragments and words associated with negativity or something not being successful

    oai_token-act-pair · gemini-2.0-flash

    let

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    :+:
    -0.73
     defaultstate
    -0.65
    Spoljašnje
    -0.61
    ecken
    -0.54
    niss
    -0.53
    rophes
    -0.53
     Brink
    -0.51
     ComVisible
    -0.50
    EndContext
    -0.50
    +#+
    -0.48
    POSITIVE LOGITS
     let
    2.31
     Let
    1.81
     lets
    1.80
    Let
    1.77
    let
    1.76
     letting
    1.76
     LET
    1.64
     Lets
    1.38
    letting
    1.37
    LET
    1.36
    Activations Density 1.965%

    No Known Activations