© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16128
    Prev
    Next
    INDEX
    Explanations

    text discussing laws and taxation specifically within the state of Arizona

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    -1.54
    state
    -1.49
     State
    -1.39
    State
    -1.37
     STATE
    -1.33
    STATE
    -1.30
     province
    -1.10
     provincial
    -1.10
     statewide
    -1.09
    getState
    -1.05
    POSITIVE LOGITS
    DebuggerNonUser
    0.77
    SharedDtor
    0.69
     виправивши
    0.57
    Przypisy
    0.54
     BorderRadius
    0.53
    Slf
    0.53
    șe
    0.53
    mybatisplus
    0.52
    modelBuilder
    0.51
     ddelweddau
    0.51
    Activations Density 12.935%

    No Known Activations