© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9616
    Prev
    Next
    INDEX
    Explanations

    words expressing a possibility or potential action

    oai_token-act-pair · gemini-2.0-flash

    possibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ")));
    -1.00
    "]);
    -0.97
    '},
    -0.96
    "])
    -0.93
     صوتيه
    -0.93
     تانيه
    -0.91
    "},
    -0.90
     purpoſe
    -0.90
     igång
    -0.88
     متعلقه
    -0.86
    POSITIVE LOGITS
    ↵
    1.02
    ↵↵
    0.75
     known
    0.61
     likely
    0.61
    1
    0.60
    3
    0.59
     menudo
    0.58
    2
    0.56
    ,
    0.56
    4
    0.55
    Activations Density 0.302%

    No Known Activations