© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11968
    Prev
    Next
    INDEX
    Explanations

    instances of verbs, especially when followed by "to" or "be".

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     Efq
    -1.01
     صوتيه
    -1.01
     houſe
    -0.96
     Majefty
    -0.95
     Theſe
    -0.93
     Houſe
    -0.90
     يتيمه
    -0.90
    ſelf
    -0.90
     purpoſe
    -0.88
     myſelf
    -0.87
    POSITIVE LOGITS
     NUnit
    0.55
     have
    0.54
     correct
    0.48
    abá
    0.45
     take
    0.43
     can
    0.43
    akesh
    0.42
     s
    0.42
     stand
    0.41
     see
    0.40
    Activations Density 2.088%

    No Known Activations