© 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. 10927
    Prev
    Next
    INDEX
    Explanations

    sentences with emotional content that include the word "am" or the word "was"

    oai_token-act-pair · gemini-2.0-flash

    personal feelings

    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
    ModelAdmin
    -0.66
     متعلقه
    -0.61
    legungen
    -0.54
     memoized
    -0.54
    MUN
    -0.53
    ensione
    -0.53
    Portály
    -0.53
     pluie
    -0.52
     hiệp
    -0.52
     zubehör
    -0.52
    POSITIVE LOGITS
     onOptions
    0.57
     moved
    0.56
     nonUne
    0.49
    createStatement
    0.47
     Meilleur
    0.47
    moved
    0.46
     MOVE
    0.45
     touched
    0.45
     distanciation
    0.44
    touched
    0.43
    Activations Density 0.916%

    No Known Activations