© 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. 10960
    Prev
    Next
    INDEX
    Explanations

    the word "state" and words that follow it

    oai_token-act-pair · gemini-2.0-flash

    state

    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
     state
    -2.50
    state
    -2.44
    STATE
    -1.60
     estado
    -1.59
     ftate
    -1.52
     states
    -1.51
     STATE
    -1.46
    states
    -1.45
    State
    -1.38
     état
    -1.38
    POSITIVE LOGITS
    Ă
    0.45
    batore
    0.45
    }}=
    0.40
    Â
    0.37
    oredCriteria
    0.37
     â
    0.37
    Bibliograf
    0.37
     रेटिंग
    0.36
    <0xE7>
    0.36
    â
    0.36
    Activations Density 0.779%

    No Known Activations